论文检索

Changshuo Wang, Shuting He, Xiang Fang, Jiawei Han, Zhonghang Liu, Xin Ning, Weijun Li, Prayag Tiwari

While existing pre-training-based methods have enhanced point cloud model performance, they have not fundamentally resolved the challenge of local structure representation in point clouds. The limited representational capacity of pure point cloud models continues to constrain the potential of cross-modal fusion methods and performance across various tasks. To address this challenge, we propose a Dynamic Acoustic Field Fitting Network (DAF-Net), inspired by physical acoustic principles. Specifically, we represent local point clouds as acoustic fields and introduce a novel Acoustic Field Convolution (AF-Conv), which treats local aggregation as an acoustic energy field modeling problem and captures fine-grained local shape awareness by dividing the local area into near field and far field. Furthermore, drawing inspiration from multi-frequency wave phenomena and dynamic convolution, we develop the Dynamic Acoustic Field Convolution (DAF-Conv) based on AF-Conv. DAF-Conv dynamically generates multiple weights based on local geometric priors, effectively enhancing adaptability to diverse geometric features. Additionally, we design a Global Shape-Aware (GSA) layer incorporating EdgeConv and multi-head attention mechanisms, which combines with DAF-Conv to form the DAF Block. These blocks are then stacked to create a hierarchical DAFNet architecture. Extensive experiments demonstrate that DAFNet significantly outperforms existing methods across multiple tasks.

Fan-Yun Sun, Weiyu Liu, Siyi Gu, Dylan Lim, Goutam Bhat, Federico Tombari, Manling Li, Nick Haber, Jiajun Wu

Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space. While foundation models demonstrate remarkable performance on some benchmarks, they still struggle with 3D reasoning tasks like arranging objects in space according to open-ended language instructions, particularly in dense and physically constrained environments. We introduce LayoutVLM, a framework and scene layout representation that exploits the semantic knowledge of Vision-Language Models (VLMs) and supports differentiable optimization to ensure physical plausibility. LayoutVLM employs VLMs to generate two mutually reinforcing representations from visually marked images, and a self-consistent decoding process to improve VLMs spatial planning. Our experiments show that LayoutVLM addresses the limitations of existing LLM and constraint-based approaches, producing physically plausible 3D layouts better aligned with the semantic intent of input language instructions. We also demonstrate that fine-tuning VLMs with the proposed scene layout representation extracted from existing scene datasets can improve their reasoning performance.

Jianwei Yang, Reuben Tan, Qianhui Wu, Ruijie Zheng, Baolin Peng, Yongyuan Liang, Yu Gu, Mu Cai, Seonghyeon Ye, Joel Jang 等

We present Magma, a foundation model that serves multimodal AI agentic tasks in both the digital and physical worlds. Magma is a significant extension of vision-language (VL) models in that it not only retains the VL understanding ability (verbal intelligence) of the latter, but is also equipped with the ability to ground and act in the visual-spatial world (spatial-temporal intelligence). To endow agentic capabilities for tasks ranging from UI navigation to robot manipulation, Magma is trained on large amounts of heterogeneous datasets that span from images, videos to robotics data, where actionable visual objects (e.g. clickable buttons in GUI) in images are labeled by Set-of-Mark (SoM) for action grounding, and object movements (e.g. trace of human hands or robotic arms) in videos are labeled by Trace-of-Mark (ToM) for action planning. Extensive experiments show that SoM and ToM help bridge the gap between verbal and action abilities and significantly enhance spatio-temporal intelligence which is fundamental to agentic tasks, as shown in Fig.1. In particular, Magma creates new state-of-the-art results on UI navigation and robotic manipulation tasks, outperforming previous models that are specifically tailored to these tasks. Moreover, Magma preserves strong multimodal understanding ability and compares favorably to popular large multimodal models that are trained on much larger datasets. We have made our model and code public for reproducibility at https://microsoft.github.io/Magma.

Jeonghwan Kim, Jisoo Kim, Jeonghyeon Na, Hanbyul Joo

To enable machines to understand the way humans interact with the physical world in daily life, 3D interaction signals should be captured in natural settings, allowing people to engage with multiple objects in a range of sequential and casual manipulations. To achieve this goal, we introduce our ParaHome system designed to capture dynamic 3D movements of humans and objects within a common home environment. Our system features a multi-view setup with 70 synchronized RGB cameras, along with wearable motion capture devices including an IMU-based body suit and hand motion capture gloves. By leveraging the ParaHome system, we collect a new human-object interaction dataset, including 486 minutes of sequences across 207 captures with 38 participants, offering advancements with three key aspects: (1) capturing body motion and dexterous hand manipulation motion alongside multiple objects within a contextual home environment; (2) encompassing sequential and concurrent manipulations paired with text descriptions; and (3) including articulated objects with multiple parts represented by 3D parameterized models. We present detailed design justifications for our system, and perform key generative modeling experiments to demonstrate the potential of our dataset.

Di Chang, Hongyi Xu, You Xie, Yipeng Gao, Zhengfei Kuang, Shengqu Cai, Chenxu Zhang, Guoxian Song, Chao Wang, Yichun Shi 等

We introduce X-Dyna, a novel zero-shot, diffusion-based pipeline for animating a single human image using facial expressions and body movements derived from a driving video, that generates realistic, context-aware dynamics for both the subject and the surrounding environment. Building on prior approaches centered on human pose control, X-Dyna addresses key factors underlying the loss of dynamic details, enhancing the lifelike qualities of human video animations.At the core of our approach is the Dynamics-Adapter, a lightweight module that effectively integrates reference appearance context into the spatial attentions of the diffusion backbone while preserving the capacity of motion modules in synthesizing fluid and intricate dynamic details. Beyond body pose control, we connect a local control module with our model to capture identity-disentangled facial expressions, facilitating accurate expression transfer for enhanced realism in animated scenes. Together, these components form a unified framework capable of learning physical human motion and natural scene dynamics from a diverse blend of human and scene videos. Comprehensive qualitative and quantitative evaluations demonstrate that X-Dyna outperforms state-of-the-art methods, creating highly lifelike and expressive animations. The code is available at https://github.com/bytedance/X-Dyna

Sanjay Subramanian, Evonne Ng, Lea Müller, Dan Klein, Shiry Ginosar, Trevor Darrell

Language is often used to describe physical interaction, yet most 3D human pose estimation methods overlook this rich source of information. We bridge this gap by leveraging large multimodal models (LMMs) as priors for reconstructing contact poses, offering a scalable alternative to traditional methods that rely on human annotations or motion capture data. Our approach extracts contact-relevant descriptors from an LMM and translates them into tractable losses to constrain 3D human pose optimization. Despite its simplicity, our method produces compelling reconstructions for both two-person interactions and self-contact scenarios, accurately capturing the semantics of physical and social interactions. Our results demonstrate that LMMs can serve as powerful tools for contact prediction and pose estimation, offering an alternative to costly manual human annotations or motion capture data. Our code is publicly available at prosepose.github.io.

Hanxiao Sun, Yupeng Gao, Jin Xie, Jian Yang, Beibei Wang

Reconstructing 3D assets from images, known as inverse rendering (IR), remains a challenging task due to its ill-posed nature. 3D Gaussian Splatting (3DGS) has demonstrated impressive capabilities for novel view synthesis (NVS) tasks. Methods apply it to relighting by separating radiance into BRDF parameters and lighting, yet produce inferior relighting quality with artifacts and unnatural indirect illumination due to the limited capability of each Gaussian, which has constant material parameters and normal, alongside the absence of physical constraints for indirect lighting. In this paper, we present a novel framework called Spatially-vayring Gaussian Inverse Rendering (SVG-IR), aimed at enhancing both NVS and relighting quality. To this end, we propose a new representation--Spatially-varying Gaussian (SVG)--that allows per-Gaussian spatially varying parameters. This enhanced representation is complemented by a SVG splatting scheme akin to vertex/fragment shading in traditional graphics pipelines. Furthermore, we integrate a physically-based indirect lighting model, enabling more realistic relighting. The proposed SVG-IR framework significantly improves rendering quality, outperforming state-of-the-art NeRF-based methods by 2.5 dB in peak signal-to-noise ratio (PSNR) and surpassing existing Gaussian-based techniques by 3.5 dB in relighting tasks, all while maintaining a real-time rendering speed. The source code is available at https://github.com/learner-shx/SVG-IR.

Zhenyu Wu, Yuheng Zhou, Xiuwei Xu, Ziwei Wang, Haibin Yan

Mobile manipulation is the fundamental challenge for robotics to assist humans with diverse tasks and environments in everyday life. However, conventional mobile manipulation approaches often struggle to generalize across different tasks and environments because of the lack of large-scale training.In contrast, recent advances in vision-language-action (VLA) models have shown impressive generalization capabilities, but these foundation models are developed for fixed-base manipulation tasks.Therefore, we propose an efficient policy adaptation framework to transfer pre-trained VLA models of fix-base manipulation to mobile manipulation, so that high generalization ability across tasks and environments can be achieved in mobile manipulation policy.Specifically, we utilize pre-trained VLA models to generate waypoints of the end-effector with high generalization ability. We design motion planning objectives for the mobile base and the robot arm, which aim at maximizing the physical feasibility of the trajectory. Finally, we present an efficient bi-level objective optimization framework for trajectory generation, where the upper-level optimization predicts waypoints for base movement to enhance the manipulator policy space, and the lower-level optimization selects the optimal end-effector trajectory to complete the manipulation task. Extensive experimental results on OVMM and the real world demonstrate that our method achieves a 4.2% higher success rate than the state-of-the-art mobile manipulation, and only requires 50 training cost for real world deployment due to the strong generalization ability in the pre-trained VLA models.

Dennis Jacob, Chong Xiang, Prateek Mittal

Deep learning techniques have enabled vast improvements in computer vision technologies. Nevertheless, these models are vulnerable to adversarial patch attacks which catastrophically impair performance. The physically realizable nature of these attacks calls for certifiable defenses, which feature provable guarantees on robustness. While certifiable defenses have been successfully applied to single-label classification, limited work has been done for multi-label classification. In this work, we present PatchDEMUX, a certifiably robust framework for multi-label classifiers against adversarial patches. Our approach is a generalizable method which can extend any existing certifiable defense for single-label classification; this is done by considering the multi-label classification task as a series of isolated binary classification problems to provably guarantee robustness. Furthermore, in the scenario where an attacker is limited to a single patch we propose an additional certification procedure that can provide tighter robustness bounds. Using the current state-of-the-art (SOTA) single-label certifiable defense PatchCleanser as a backbone, we find that PatchDEMUX can achieve non-trivial robustness on the MS-COCO and PASCAL VOC datasets while maintaining high clean performance

Bonan Li, Zicheng Zhang, Xingyi Yang, Xinchao Wang

Generating dense multiview images from text prompts is crucial for creating high-fidelity 3D assets. Nevertheless, existing methods struggle with space-view correspondences, resulting in sparse and low-quality outputs. In this paper, we introduce CoSER, a novel consistent dense Multiview Text-to-Image Generator for Text-to-3D, achieving both efficiency and quality by meticulously learning neighbor-view coherence and further alleviating ambiguity through the swift traversal of all views. For achieving neighbor-view consistency, each viewpoint densely interacts with adjacent viewpoints to perceive the global spatial structure, and aggregates information along motion paths explicitly defined by physical principles to refine details. To further enhance cross-view consistency and alleviate content drift, CoSER rapidly scan all views in spiral bidirectional manner to aware holistic information and then scores each point based on semantic material. Subsequently, we conduct weighted down-sampling along the spatial dimension based on scores, thereby facilitating prominent information fusion across all views with lightweight computation. Technically, the core module is built by integrating the attention mechanism with a selective state space model, exploiting the robust learning capabilities of the former and the low overhead of the latter. Extensive evaluation shows that CoSER is capable of producing dense, high-fidelity, content-consistent multiview images that can be flexibly integrated into various 3D generation models.

Xiaoling Zhou, Zhemg Lee, Wei Ye, Rui Xie, Wenbo Zhang, Guanju Peng, Zongze Li, Shikun Zhang

Image denoising poses a significant challenge in image processing, aiming to remove noise and artifacts from input images. However, current denoising algorithms implemented on electronic chips frequently encounter latency issues and demand substantial computational resources. In this paper, we introduce an all-optical Nonlinear Diffractive Denoising Deep Network (N3DNet) for image denoising at the speed of light. Initially, we incorporate an image encoding and pre-denoising module into the Diffractive Deep Neural Network and integrate a nonlinear activation function, termed the phase exponential linear function, after each diffractive layer, thereby boosting the network's nonlinear modeling and denoising capabilities. Subsequently, we devise a new reinforcement learning algorithm called regularization-assisted deep Q-network to optimize N3DNet. Finally, leveraging 3D printing techniques, we fabricate N3DNet using the trained parameters and construct a physical experimental system for real-world applications. A new benchmark dataset, termed MIDD, is constructed for mode image denoising, comprising 120K pairs of noisy/noise-free images captured from real fiber communication systems across various transmission lengths. Through extensive simulation and real experiments, we validate that N3DNet outperforms both traditional and deep learning-based denoising approaches across various datasets. Remarkably, its processing speed is nearly 3,800 times faster than electronic chip-based methods.

Jinxi Li, Ziyang Song, Siyuan Zhou, Bo Yang

In this paper, we aim to model 3D scene geometry, appearance, and the underlying physics purely from multi-view videos. By applying various governing PDEs as PINN losses or incorporating physics simulation into neural networks, existing works often fail to learn complex physical motions at boundaries or require object priors such as masks or types. In this paper, we propose FreeGave to learn physics of complex dynamic 3D scenes without needing any object priors. The key to our approach is to introduce a physics code followed by a carefully designed divergence-free module for estimating a per-Gaussian velocity field, without relying on the inefficient PINN losses. Extensive experiments on three public datasets and a newly collected challenging real-world dataset demonstrate the superior performance of our method for future frame extrapolation and motion segmentation. Most notably, our investigation into the learned physics codes reveals that they truly learn meaningful 3D physical motion patterns in the absence of any human labels in training. Our code and data are available at https://github.com/vLAR-group/FreeGave.

Raktim Gautam Goswami, Prashanth Krishnamurthy, Yann LeCun, Farshad Khorrami

Vision-based pose estimation of articulated robots with unknown joint angles has applications in collaborative robotics and human-robot interaction tasks. Current frameworks use neural network encoders to extract image features and downstream layers to predict joint angles and robot pose. While images of robots inherently contain rich information about the robot's physical structures, existing methods often fail to leverage it fully; therefore, limiting performance under occlusions and truncations. To address this, we introduce RoboPEPP, a method that fuses information about the robot's physical model into the encoder using a masking-based self-supervised embedding-predictive architecture. Specifically, we mask the robot's joints and pre-train an encoder-predictor model to infer the joints' embeddings from surrounding unmasked regions, enhancing the encoder's understanding of the robot's physical model. The pre-trained encoder-predictor pair, along with joint angle and keypoint prediction networks, is then fine-tuned for pose and joint angle estimation. Random masking of input during fine-tuning and keypoint filtering during evaluation further improves robustness. Our method, evaluated on several datasets, achieves the best results in robot pose and joint angle estimation while being the least sensitive to occlusions and requiring the lowest execution time.

Yuxiang Fu, Qi Yan, Lele Wang, Ke Li, Renjie Liao

In this paper, we address the problem of human trajectory forecasting, which aims to predict the inherently multi-modal future movements of humans based on their past trajectories and other contextual cues. We propose a novel motion prediction conditional flow matching model, termed MoFlow, to predict K-shot future trajectories for all agents in a given scene. We design a novel flow matching loss function that not only ensures at least one of the K sets of future trajectories is accurate but also encourages all K sets of future trajectories to be diverse and plausible. Furthermore, by leveraging the implicit maximum likelihood estimation (IMLE), we propose a novel distillation method for flow models that only requires samples from the teacher model. Extensive experiments on the real-world datasets, including SportVU NBA games, ETH-UCY, and SDD, demonstrate that both our teacher flow model and the IMLE-distilled student model achieve state-of-the-art performance. These models can generate diverse trajectories that are physically and socially plausible. Moreover, our one-step student model is 100 times faster than the teacher flow model during sampling. The code, model, and data are available at our project page: https://moflow-imle.github.io/.

Bin Ji, Ye Pan, Zhimeng Liu, Shuai Tan, Xiaogang Jin, Xiaokang Yang

Numerous researches on real-time motion generation primarily focus on kinematic aspects, often resulting in physically implausible outcomes. In this paper, we present POMP ("\underline P hysics-c\underline O nsistent Human \underline M otion \underline P rior through Phase Manifolds"), a novel kinematics-based framework that synthesizes physically consistent motions by leveraging phase manifolds to align motion priors with physics constraints. POMP operates as a frame-by-frame autoregressive model with three core components: a diffusion-based kinematic module, a simulation-based dynamic module, and a phase encoding module. At each timestep, the kinematic module generates an initial target pose, which is subsequently refined by the dynamic module to simulate human-environment interactions. Although the physical simulation ensures adherence to physical laws, it may compromise the kinematic rationality of the posture. Consequently, directly using the simulated result for subsequent frame prediction may lead to cumulative errors. To address this, the phase encoding module performs semantic alignment in the phase manifold. Moreover, we present a pipeline in Unity for generating terrain maps and capturing full-body motion impulses from existing motion capture (MoCap) data. The collected terrain topology and motion impulse data facilitate the training of POMP, enabling it to robustly respond to underlying contactforces and applied dynamics. Extensive evaluations demonstrate the efficacy of POMP across various contexts, terrains, and physical interactions.

Anagh Malik, Benjamin Attal, Andrew Xie, Matthew O'Toole, David B. Lindell

We present the first system for physically based, neural inverse rendering from multi-viewpoint videos of propagating light. Our approach relies on a time-resolved extension of neural radiance caching -- a technique that accelerates inverse rendering by storing infinite-bounce radiance arriving at any point from any direction. The resulting model accurately accounts for direct and indirect light transport effects and, when applied to captured measurements from a flash lidar system, enables state-of-the-art 3D reconstruction in the presence of strong indirect light. Further, we demonstrate view synthesis of propagating light, automatic decomposition of captured measurements into direct and indirect components, as well as novel capabilities such as multi-view time-resolved relighting of captured scenes.

Peishan Cong, Ziyi Wang, Yuexin Ma, Xiangyu Yue

Generating reasonable and high-quality human interactive motions in a given dynamic environment is crucial for understanding, modeling, transferring, and applying human behaviors to both virtual and physical robots. In this paper, we introduce an effective method, SemGeoMo, for dynamic contextual human motion generation, which fully leverages the text-affordance-joint multi-level semantic and geometric guidance in the generation process, improving the semantic rationality and geometric correctness of generative motions. Our method achieves state-of-the-art performance on three datasets and demonstrates superior generalization capability for diverse interaction scenarios.

Hoon-Gyu Chung, Seokjun Choi, Seung-Hwan Baek

Inverse rendering seeks to reconstruct both geometry and spatially varying BRDFs (SVBRDFs) from captured images. To address the inherent ill-posedness of inverse rendering, basis BRDF representations are commonly used, modeling SVBRDFs as spatially varying blends of a set of basis BRDFs. However, existing methods often yield basis BRDFs that lack intuitive separation and have limited scalability to scenes of varying complexity. In this paper, we introduce a differentiable inverse rendering method that produces interpretable basis BRDFs. Our approach models a scene using 2D Gaussians, where the reflectance of each Gaussian is defined by a weighted blend of basis BRDFs. We efficiently render an image from the 2D Gaussians and basis BRDFs using differentiable rasterization and impose a specular-weighted rendering loss with the input flash photography images. During this analysis-by-synthesis optimization process of differentiable inverse rendering, we dynamically adjust the number of basis BRDFs to fit the target scene while encouraging sparsity in the basis weights. This ensures that the reflectance of each Gaussian is represented by only a few basis BRDFs. This approach enables the reconstruction of accurate geometry and interpretable basis BRDFs that are spatially separated. Consequently, the resulting scene representation, comprising basis BRDFs and 2D Gaussians, supports physically-based novel-view relighting and intuitive scene editing.

Zhuoman Liu, Weicai Ye, Yan Luximon, Pengfei Wan, Di Zhang

Realistic simulation of dynamic scenes requires accurately capturing diverse material properties and modeling complex object interactions grounded in physical principles. However, existing methods are constrained to basic material types with limited predictable parameters, making them insufficient to represent the complexity of real-world materials. We introduce PhysFlow, a novel approach that leverages multi-modal foundation models and video diffusion to achieve enhanced 4D dynamic scene simulation. Our method utilizes multi-modal models to identify material types and initialize material parameters through image queries, while simultaneously inferring 3D Gaussian splats for detailed scene representation. We further refine these material parameters using video diffusion with a differentiable Material Point Method (MPM) and optical flow guidance rather than render loss or Score Distillation Sampling (SDS) loss. This integrated framework enables accurate prediction and realistic simulation of dynamic interactions in real-world scenarios, advancing both accuracy and flexibility in physics-based simulations.

Guangyan Chen, Te Cui, Meiling Wang, Chengcai Yang, Mengxiao Hu, Haoyang Lu, Yao Mu, Zicai Peng, Tianxing Zhou, Xinran Jiang 等

Learning from demonstration is a powerful method for robotic skill acquisition. However, the significant expense of collecting such action-labeled robot data presents a major bottleneck. Video data, a rich data source encompassing diverse behavioral and physical knowledge, emerges as a promising alternative. In this paper, we present GraphMimic, a novel paradigm that leverages video data via graph-to-graphs generative modeling, which pre-trains models to generate future graphs conditioned on the graph within a video frame. Specifically, GraphMimic abstracts video frames into object and visual action vertices, and constructs graphs for state representations. The graph generative modeling network then effectively models internal structures and spatial relationships within the constructed graphs, aiming to generate future graphs. The generated graphs serve as conditions for the control policy, mapping to robot actions. Our concise approach captures important spatial relations and enhances future graph generation accuracy, enabling the acquisition of robust policies from limited action-labeled data. Furthermore, the transferable graph representations facilitate the effective learning of manipulation skills from cross-embodiment videos. Our experiments exhibit that GraphMimic achieves superior performance using merely 20% action-labeled data. Moreover, our method outperforms the state-of-the-art method by over 17% and 23% in simulation and real-world experiments, and delivers improvements of over 33% in cross-embodiment transfer experiments.