44 citations · 235 across the 56 of their papers we have counts for
63 papers
Scaling Discovery Requires Forgetting
Shangyin Tan, Ben Zhou, Lakshya A Agrawal +8
Automated research with LLM agents has shown promising results in various domains. Through iterative refinement and scored verifiers, LLM agents are capable of discovering new idea…
PointSplat: Compact Gaussian Splatting via Human-Centric Prediction
Yujie Guo, Yudong Jin, Lingteng Qiu +7
Producing 3D human representations from input views on the fly is essential for immersive live streaming systems, where representation compactness is as critical as high fidelity g…
Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting
Ziyuan Xia, Jingyi Xu, Chong Cui +9
Training embodied AI agents depends critically on the visual fidelity of simulation environments and the ability to model dynamic humans. Current simulators predominantly rely on m…
Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
Tao Xie, Peishan Yang, Yudong Jin +8
This paper addresses the task of large-scale 3D scene reconstruction from long video sequences. Recent feed-forward reconstruction models have shown promising results by directly r…
SpatialTree: How Spatial Abilities Branch Out in MLLMs
Yuxi Xiao, Longfei Li, Shen Yan +5
Cognitive science suggests that spatial ability develops progressively-from perception to reasoning and interaction. Yet in multimodal LLMs (MLLMs), this hierarchy remains poorly u…
Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation
Yongzhen Hu, Yihui Yang, Haotong Lin +8
This paper addresses the problem of decomposed 4D scene reconstruction from multi-view videos. Recent methods achieve this by lifting video segmentation results to a 4D representat…
StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model
Yifan Yang, Zhi Cen, Sida Peng +6
This paper focuses on the task of speech-driven 3D facial animation, which aims to generate realistic and synchronized facial motions driven by speech inputs. Recent methods have e…
ERNet: Efficient Non-Rigid Registration Network for Point Sequences
Guangzhao He, Yuxi Xiao, Zhen Xu +2
Registering an object shape to a sequence of point clouds undergoing non-rigid deformation is a long-standing challenge. The key difficulties stem from two factors: (i) the presenc…
UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction
Jin Cao, Hongrui Wu, Ziyong Feng +3
This paper tackles the challenge of robust reconstruction, i.e., the task of reconstructing a 3D scene from a set of inconsistent multi-view images. Some recent works have attempte…
Precise Action-to-Video Generation Through Visual Action Prompts
Yuang Wang, Chao Wen, Haoyu Guo +5
We present visual action prompts, a unified action representation for action-to-video generation of complex high-DoF interactions while maintaining transferable visual dynamics acr…
Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models
Yudong Jin, Sida Peng, Xuan Wang +6
This paper addresses the challenge of high-fidelity view synthesis of humans with sparse-view videos as input. Previous methods solve the issue of insufficient observation by lever…
Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation
Zhen Xu, Hongyu Zhou, Sida Peng +13
Depth estimation is a fundamental task in 3D computer vision, crucial for applications such as 3D reconstruction, free-viewpoint rendering, robotics, autonomous driving, and AR/VR…
BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation
Yuanhong Yu, Xingyi He, Chen Zhao +7
This paper presents a generalizable RGB-based approach for object pose estimation, specifically designed to address challenges in sparse-view settings. While existing methods can e…
Multi-view Reconstruction via SfM-guided Monocular Depth Estimation
Haoyu Guo, He Zhu, Sida Peng +6
In this paper, we present a new method for multi-view geometric reconstruction. In recent years, large vision models have rapidly developed, performing excellently across various t…
MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space
Lixing Xiao, Shunlin Lu, Huaijin Pi +7
This paper addresses the challenge of text-conditioned streaming motion generation, which requires us to predict the next-step human pose based on variable-length historical motion…
Mocap-2-to-3: Multi-view Lifting for Monocular Motion Recovery with 2D Pretraining
Zhumei Wang, Zechen Hu, Ruoxi Guo +5
Human motion recovery for real-world interaction demands both precise action details and metric-scale trajectories. Recovering absolute human pose from monocular input presents a v…
Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation
Zhi Cen, Huaijin Pi, Sida Peng +5
This paper addresses the task of generating two-character online interactions. Previously, two main settings existed for two-character interaction generation: (1) generating one's…
MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training
Xingyi He, Hao Yu, Sida Peng +4
Image matching, which aims to identify corresponding pixel locations between images, is crucial in a wide range of scientific disciplines, aiding in image registration, fusion, and…
Representing Long Volumetric Video with Temporal Gaussian Hierarchy
Zhen Xu, Yinghao Xu, Zhiyuan Yu +4
This paper aims to address the challenge of reconstructing long volumetric videos from multi-view RGB videos. Recent dynamic view synthesis methods leverage powerful 4D representat…
EnvGS: Modeling View-Dependent Appearance with Environment Gaussian
Tao Xie, Xi Chen, Zhen Xu +6
Reconstructing complex reflections in real-world scenes from 2D images is essential for achieving photorealistic novel view synthesis. Existing methods that utilize environment map…
Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation
Haotong Lin, Sida Peng, Jingxiao Chen +7
Prompts play a critical role in unleashing the power of language and vision foundation models for specific tasks. For the first time, we introduce prompting into depth foundation m…
StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
Yunzhi Yan, Zhen Xu, Haotong Lin +8
This paper aims to tackle the problem of photorealistic view synthesis from vehicle sensor data. Recent advancements in neural scene representation have achieved notable success in…
Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations
Ruoxi Guo, Huaijin Pi, Zehong Shen +8
Text-driven human motion synthesis has showcased its potential for revolutionizing motion design in the movie and game industry. Existing methods often rely on 3D motion capture da…
World-Grounded Human Motion Recovery via Gravity-View Coordinates
Zehong Shen, Huaijin Pi, Yan Xia +6
We present a novel method for recovering world-grounded human motion from monocular video. The main challenge lies in the ambiguity of defining the world coordinate system, which v…