32 citations · 94 across the 29 of their papers we have counts for
31 papers
tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
Chen Wang, Hao Tan, Wang Yifan +6
We propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive 3D reconstruction with linear comput…
RELIC: Interactive Video World Model with Long-Horizon Memory
Yicong Hong, Yiqun Mei, Chongjian Ge +11
A truly interactive world model requires three key ingredients: real-time long-horizon streaming, consistent spatial memory, and precise user control. However, most existing approa…
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…
pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
Hansheng Chen, Kai Zhang, Hao Tan +3
Few-step diffusion or flow-based generative models typically distill a velocity-predicting teacher into a student that predicts a shortcut towards denoised data. This format mismat…
AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models
Bowei Chen, Sai Bi, Hao Tan +6
In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE)…
KnapFormer: An Online Load Balancer for Efficient Diffusion Transformers Training
Kai Zhang, Peng Wang, Sai Bi +2
We present KnapFormer, an efficient and versatile framework to combine workload balancing and sequence parallelism in distributed training of Diffusion Transformers (DiT). KnapForm…
4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time
Ziqiao Ma, Xuweiyi Chen, Shoubin Yu +10
Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at some times to any view at any time? We provide an affirmative…
Test-Time Training Done Right
Tianyuan Zhang, Sai Bi, Yicong Hong +6
Test-Time Training (TTT) models context dependencies by adapting part of the model's weights (referred to as fast weights) during inference. This fast weight, akin to recurrent sta…
Neural BRDF Importance Sampling by Reparameterization
Liwen Wu, Sai Bi, Zexiang Xu +5
Neural bidirectional reflectance distribution functions (BRDFs) have emerged as popular material representations for enhancing realism in physically-based rendering. Yet their impo…
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…
Gaussian Mixture Flow Matching Models
Hansheng Chen, Kai Zhang, Hao Tan +5
Diffusion models approximate the denoising distribution as a Gaussian and predict its mean, whereas flow matching models reparameterize the Gaussian mean as flow velocity. However,…
EP-CFG: Energy-Preserving Classifier-Free Guidance
Kai Zhang, Fujun Luan, Sai Bi +1
Classifier-free guidance (CFG) is widely used in diffusion models but often introduces over-contrast and over-saturation artifacts at higher guidance strengths. We present EP-CFG (…
Turbo3D: Ultra-fast Text-to-3D Generation
Hanzhe Hu, Tianwei Yin, Fujun Luan +6
We present Turbo3D, an ultra-fast text-to-3D system capable of generating high-quality Gaussian splatting assets in under one second. Turbo3D employs a rapid 4-step, 4-view diffusi…
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 -…
Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors
Zhengfei Kuang, Tianyuan Zhang, Kai Zhang +7
We present Buffer Anytime, a framework for estimation of depth and normal maps (which we call geometric buffers) from video that eliminates the need for paired video--depth and vid…
KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos
Gene Chou, Kai Zhang, Sai Bi +5
We address the problem of generating videos from unposed internet photos. A handful of input images serve as keyframes, and our model interpolates between them to simulate a path m…
RelitLRM: Generative Relightable Radiance for Large Reconstruction Models
Tianyuan Zhang, Zhengfei Kuang, Haian Jin +9
We propose RelitLRM, a Large Reconstruction Model (LRM) for generating high-quality Gaussian splatting representations of 3D objects under novel illuminations from sparse (4-8) pos…
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…
Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats
Chen Ziwen, Hao Tan, Kai Zhang +5
We propose Long-LRM, a feed-forward 3D Gaussian reconstruction model for instant, high-resolution, 360° wide-coverage, scene-level reconstruction. Specifically, it takes in 32 inpu…
PBIR-NIE: Glossy Object Capture under Non-Distant Lighting
Guangyan Cai, Fujun Luan, Miloš Hašan +5
Glossy objects present a significant challenge for 3D reconstruction from multi-view input images under natural lighting. In this paper, we introduce PBIR-NIE, an inverse rendering…
LRM-Zero: Training Large Reconstruction Models with Synthesized Data
Desai Xie, Sai Bi, Zhixin Shu +7
We present LRM-Zero, a Large Reconstruction Model (LRM) trained entirely on synthesized 3D data, achieving high-quality sparse-view 3D reconstruction. The core of LRM-Zero is our p…
Neural Gaffer: Relighting Any Object via Diffusion
Haian Jin, Yuan Li, Fujun Luan +6
Single-image relighting is a challenging task that involves reasoning about the complex interplay between geometry, materials, and lighting. Many prior methods either support only…
GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting
Kai Zhang, Sai Bi, Hao Tan +4
We propose GS-LRM, a scalable large reconstruction model that can predict high-quality 3D Gaussian primitives from 2-4 posed sparse images in 0.23 seconds on single A100 GPU. Our m…
MeshLRM: Large Reconstruction Model for High-Quality Meshes
Xinyue Wei, Kai Zhang, Sai Bi +6
We propose MeshLRM, a novel LRM-based approach that can reconstruct a high-quality mesh from merely four input images in less than one second. Different from previous large reconst…