34 citations · 43 across the 13 of their papers we have counts for
17 papers
FADE: Frame-Aware Diffusion-Transformer-based Multi-Concept Erasure for Video Unlearning
Yuchen Li, Kaiyuan Deng, Chaoran Feng +2
Text-to-video (T2V) diffusion models can reproduce copyrighted, violent, or explicit content, which motivates concept erasure: removing designated concepts from a pretrained model…
SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation
Juncheng Ma, Yuxuan Du, Yanan Sun +8
Diffusion Transformers (DiTs) have significantly advanced audio-driven portrait animation, but their high computational cost leads to substantial inference latency. Although traini…
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models
Shengjun Zhang, Zhang Zhang, Simin Huang +11
Recent advancements in video-based world models have demonstrated an unprecedented ability to synthesize high-fidelity visual sequences. However, a fundamental gap persists between…
Enhancing Spatial Understanding in Image Generation via Reward Modeling
Zhenyu Tang, Chaoran Feng, Yufan Deng +5
Recent progress in text-to-image generation has greatly advanced visual fidelity and creativity, but it has also imposed higher demands on prompt complexity-particularly in encodin…
E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras
Chaoran Feng, Zhenyu Tang, Wangbo Yu +5
Novel view synthesis and 4D reconstruction techniques predominantly rely on RGB cameras, thereby inheriting inherent limitations such as the dependence on adequate lighting, suscep…
Epona: Autoregressive Diffusion World Model for Autonomous Driving
Kaiwen Zhang, Zhenyu Tang, Xiaotao Hu +9
Diffusion models have demonstrated exceptional visual quality in video generation, making them promising for autonomous driving world modeling. However, existing video diffusion-ba…
GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation
Yuchen Li, Chaoran Feng, Zhenyu Tang +4
We introduce GS2E (Gaussian Splatting to Event), a large-scale synthetic event dataset for high-fidelity event vision tasks, captured from real-world sparse multi-view RGB images.…
NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations
Zhenyu Tang, Chaoran Feng, Xinhua Cheng +6
3D Gaussian Splatting (3DGS) achieves impressive quality and rendering speed, but with millions of 3D Gaussians and significant storage and transmission costs. In this paper, we ai…
AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scene
Chaoran Feng, Wangbo Yu, Xinhua Cheng +4
Compared to frame-based methods, computational neuromorphic imaging using event cameras offers significant advantages, such as minimal motion blur, enhanced temporal resolution, an…
Next Patch Prediction for Autoregressive Visual Generation
Yatian Pang, Peng Jin, Shuo Yang +8
Autoregressive models, built based on the Next Token Prediction (NTP) paradigm, show great potential in developing a unified framework that integrates both language and vision task…
Open-Sora Plan: Open-Source Large Video Generation Model
Bin Lin, Yunyang Ge, Xinhua Cheng +21
We introduce Open-Sora Plan, an open-source project that aims to contribute a large generation model for generating desired high-resolution videos with long durations based on vari…
Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle
Zhenyu Tang, Junwu Zhang, Xinhua Cheng +5
Recent 3D large reconstruction models typically employ a two-stage process, including first generate multi-view images by a multi-view diffusion model, and then utilize a feed-forw…
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
Lin Chen, Xilin Wei, Jinsong Li +12
We present the ShareGPT4Video series, aiming to facilitate the video understanding of large video-language models (LVLMs) and the video generation of text-to-video models (T2VMs) v…
Envision3D: One Image to 3D with Anchor Views Interpolation
Yatian Pang, Tanghui Jia, Yujun Shi +6
We present Envision3D, a novel method for efficiently generating high-quality 3D content from a single image. Recent methods that extract 3D content from multi-view images generate…
LLMBind: A Unified Modality-Task Integration Framework
Bin Zhu, Munan Ning, Peng Jin +7
Despite recent progress in Multi-Modal Large Language Models (MLLMs), it remains challenging to integrate diverse tasks ranging from pixel-level perception to high-fidelity generat…
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Bin Lin, Zhenyu Tang, Yang Ye +7
Recent advances demonstrate that scaling Large Vision-Language Models (LVLMs) effectively improves downstream task performances. However, existing scaling methods enable all model…
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
Junwu Zhang, Zhenyu Tang, Yatian Pang +5
Recent one image to 3D generation methods commonly adopt Score Distillation Sampling (SDS). Despite the impressive results, there are multiple deficiencies including multi-view inc…