14 papers
Level-of-Token Diffusion
Kiyohiro Nakayama, Brian Chao, Jan Ackermann +5
Image and video diffusion models allocate equal computation to every region, even when the intended scene calls for varying levels of detail. The spatial distribution of detail can…
Mode Seeking meets Mean Seeking for Fast Long Video Generation
Shengqu Cai, Weili Nie, Chao Liu +8
Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to…
SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training
Yang Zheng, Hao Tan, Kai Zhang +4
The rise of 3D Gaussian Splatting has revolutionized photorealistic 3D asset creation, yet a critical gap remains for their interactive refinement and editing. Existing approaches…
SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling
Elisabetta Fedele, Francis Engelmann, Ian Huang +3
Generative methods for 3D assets have recently achieved remarkable progress, yet providing intuitive and precise control over the object geometry remains a key challenge. Existing…
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…
Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction
Youming Deng, Wenqi Xian, Guandao Yang +4
In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion and 3D Gaussian representations, enabling accurate and efficient sc…
Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images
Boyang Deng, Songyou Peng, Kyle Genova +4
We present a system using Multimodal LLMs (MLLMs) to analyze a large database with tens of millions of images captured at different times, with the aim of discovering patterns in t…
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,…
GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling
Yang Zheng, Menglei Chai, Delio Vicini +5
We present GroomLight, a novel method for relightable hair appearance modeling from multi-view images. Existing hair capture methods struggle to balance photorealistic rendering wi…
FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement
Ian Huang, Yanan Bao, Karen Truong +4
Scene generation with 3D assets presents a complex challenge, requiring both high-level semantic understanding and low-level geometric reasoning. While Multimodal Large Language Mo…
Synthesizing 3D Abstractions by Inverting Procedural Buildings with Transformers
Maximilian Dax, Jordi Berbel, Jan Stria +2
We generate abstractions of buildings, reflecting the essential aspects of their geometry and structure, by learning to invert procedural models. We first build a dataset of abstra…
3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation
Hansheng Chen, Bokui Shen, Yulin Liu +7
Multi-view image diffusion models have significantly advanced open-domain 3D object generation. However, most existing models rely on 2D network architectures that lack inherent 3D…
ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images
Xiaoshuai Zhang, Zhicheng Wang, Howard Zhou +5
To advance the state of the art in the creation of 3D foundation models, this paper introduces the ConDense framework for 3D pre-training utilizing existing pre-trained 2D networks…
Generic 3D Diffusion Adapter Using Controlled Multi-View Editing
Hansheng Chen, Ruoxi Shi, Yulin Liu +5
Open-domain 3D object synthesis has been lagging behind image synthesis due to limited data and higher computational complexity. To bridge this gap, recent works have investigated…