358 citations · 387 across the 27 of their papers we have counts for
29 papers
StableGrasp: Reconstructing Physically Stable Human Hand Grasps from Single Images
Han Jiang, Etienne Vouga, Qixing Huang +1
Reconstructing a physically stable human grasp from a single RGB image is challenging because physically modeling grasps is itself difficult, and the problem requires estimating no…
Learning Length-Extrapolatable Recurrent Models
Hanwen Jiang
Recurrent models provide a natural path to long-context modeling, yet models trained with backpropagation through time (BPTT) often fail beyond their training horizon. Classical an…
Revisiting Spectral Representations in Generative Diffusion Models
Yuehao Wang, Peihao Wang, Hanwen Jiang +3
Diffusion models have shown remarkable performance on diverse generation tasks. Recent work finds that imposing representation alignment on the hidden states of diffusion networks…
Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers
Chongjian Ge, Hanwen Jiang, Tianyu Wang +9
Visual generation increasingly requires high-resolution images, long videos, and multimodal context, making the quadratic cost of full attention prohibitive. We introduce Chimera,…
Wonder: Video World Model Done Better
Jiacong Xu, Hanwen Jiang, Zhixin Shu +3
We present Wonder, a general-purpose video world model for real-time, camera-controllable world exploration. Given an image or a conditional video, Wonder constructs a playable wor…
HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image
Hezhen Hu, Wangbo Zhao, Lanqing Guo +6
In this paper, we present HumanNOVA, a photorealistic, universal, and rapid model for generating 3D human avatars from a single RGB image. Achieving both photorealism and generaliz…
Mining Attribute Subspaces for Efficient Fine-tuning of 3D Foundation Models
Yu Jiang, Hanwen Jiang, Ahmed Abdelkader +4
With the emergence of 3D foundation models, there is growing interest in fine-tuning them for downstream tasks, where LoRA is the dominant fine-tuning paradigm. As 3D datasets exhi…
MotiMotion: Motion-Controlled Video Generation with Visual Reasoning
Lee Hsin-Ying, Hanwen Jiang, Yiqun Mei +3
Current motion-controlled image-to-video generation models rigidly follow user-provided trajectories that are often sparse, imprecise, and causally incomplete. Such reliance often…
Spherical Leech Quantization for Visual Tokenization and Generation
Yue Zhao, Hanwen Jiang, Zhenlin Xu +3
Non-parametric quantization has received much attention due to its efficiency on parameters and scalability to a large codebook. In this paper, we present a unified formulation of…
WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling
Shaoheng Fang, Hanwen Jiang, Yunpeng Bai +2
Recent video generators achieve striking photorealism, yet remain fundamentally inconsistent in 3D. We present WorldReel, a 4D video generator that is natively spatio-temporally co…
Auto3R: Automated 3D Reconstruction and Scanning via Data-driven Uncertainty Quantification
Chentao Shen, Sizhe Zheng, Bingqian Wu +5
Traditional high-quality 3D scanning and reconstruction typically relies on human labor to plan the scanning procedure. With the rapid development of embodied systems such as drone…
E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training
Qitao Zhao, Hao Tan, Qianqian Wang +5
Self-supervised pre-training has driven rapid progress in foundation models for language, 2D images, and video, yet remains largely unexplored for learning 3D-aware representations…
RayZer: A Self-supervised Large View Synthesis Model
Hanwen Jiang, Hao Tan, Peng Wang +8
We present RayZer, a self-supervised multi-view 3D Vision model trained without any 3D supervision, i.e., camera poses and scene geometry, while exhibiting emerging 3D awareness. C…
MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data
Hanwen Jiang, Zexiang Xu, Desai Xie +11
We propose scaling up 3D scene reconstruction by training with synthesized data. At the core of our work is MegaSynth, a procedurally generated 3D dataset comprising 700K scenes -…
LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias
Haian Jin, Hanwen Jiang, Hao Tan +6
We propose the Large View Synthesis Model (LVSM), a novel transformer-based approach for scalable and generalizable novel view synthesis from sparse-view inputs. We introduce two a…
Atlas Gaussians Diffusion for 3D Generation
Haitao Yang, Yuan Dong, Hanwen Jiang +3
Using the latent diffusion model has proven effective in developing novel 3D generation techniques. To harness the latent diffusion model, a key challenge is designing a high-fidel…
Real3D: Scaling Up Large Reconstruction Models with Real-World Images
Hanwen Jiang, Qixing Huang, Georgios Pavlakos
The default strategy for training single-view Large Reconstruction Models (LRMs) follows the fully supervised route using large-scale datasets of synthetic 3D assets or multi-view…
CoFie: Learning Compact Neural Surface Representations with Coordinate Fields
Hanwen Jiang, Haitao Yang, Georgios Pavlakos +1
This paper introduces CoFie, a novel local geometry-aware neural surface representation. CoFie is motivated by the theoretical analysis of local SDFs with quadratic approximation.…
OmniGlue: Generalizable Feature Matching with Foundation Model Guidance
Hanwen Jiang, Arjun Karpur, Bingyi Cao +2
The image matching field has been witnessing a continuous emergence of novel learnable feature matching techniques, with ever-improving performance on conventional benchmarks. Howe…
LEAP: Liberate Sparse-view 3D Modeling from Camera Poses
Hanwen Jiang, Zhenyu Jiang, Yue Zhao +1
Are camera poses necessary for multi-view 3D modeling? Existing approaches predominantly assume access to accurate camera poses. While this assumption might hold for dense views, a…
Pose-Free Generalizable Rendering Transformer
Zhiwen Fan, Panwang Pan, Peihao Wang +6
In the field of novel-view synthesis, the necessity of knowing camera poses (e.g., via Structure from Motion) before rendering has been a common practice. However, the consistent a…
Doduo: Learning Dense Visual Correspondence from Unsupervised Semantic-Aware Flow
Zhenyu Jiang, Hanwen Jiang, Yuke Zhu
Dense visual correspondence plays a vital role in robotic perception. This work focuses on establishing the dense correspondence between a pair of images that captures dynamic scen…
Single-Stage Visual Query Localization in Egocentric Videos
Hanwen Jiang, Santhosh Kumar Ramakrishnan, Kristen Grauman
Visual Query Localization on long-form egocentric videos requires spatio-temporal search and localization of visually specified objects and is vital to build episodic memory system…
POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference
Zhiwen Fan, Panwang Pan, Peihao Wang +4
Despite the significant progress in six degrees-of-freedom (6DoF) object pose estimation, existing methods have limited applicability in real-world scenarios involving embodied age…