65 citations · 160 across the 14 of their papers we have counts for
14 papers
Efficient-NeRF2NeRF: Streamlining Text-Driven 3D Editing with Multiview Correspondence-Enhanced Diffusion Models
Liangchen Song, Liangliang Cao, Jiatao Gu +3
The advancement of text-driven 3D content editing has been blessed by the progress from 2D generative diffusion models. However, a major obstacle hindering the widespread adoption…
Relit-NeuLF: Efficient Relighting and Novel View Synthesis via Neural 4D Light Field
Zhong Li, Liangchen Song, Zhang Chen +4
In this paper, we address the problem of simultaneous relighting and novel view synthesis of a complex scene from multi-view images with a limited number of light sources. We propo…
Efficient-3DiM: Learning a Generalizable Single-image Novel-view Synthesizer in One Day
Yifan Jiang, Hao Tang, Jen-Hao Rick Chang +3
The task of novel view synthesis aims to generate unseen perspectives of an object or scene from a limited set of input images. Nevertheless, synthesizing novel views from a single…
NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions
Zhang Chen, Zhong Li, Liangchen Song +4
We present a novel type of neural fields that uses general radial bases for signal representation. State-of-the-art neural fields typically rely on grid-based representations for s…
RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture
Liangchen Song, Liangliang Cao, Hongyu Xu +4
The techniques for 3D indoor scene capturing are widely used, but the meshes produced leave much to be desired. In this paper, we propose "RoomDreamer", which leverages powerful na…
Harnessing Low-Frequency Neural Fields for Few-Shot View Synthesis
Liangchen Song, Zhong Li, Xuan Gong +4
Neural Radiance Fields (NeRF) have led to breakthroughs in the novel view synthesis problem. Positional Encoding (P.E.) is a critical factor that brings the impressive performance…
Progressive Multi-view Human Mesh Recovery with Self-Supervision
Xuan Gong, Liangchen Song, Meng Zheng +5
To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e.g., motion capture, sport analysis) and robustness to single-vie…
Federated Learning with Privacy-Preserving Ensemble Attention Distillation
Xuan Gong, Liangchen Song, Rishi Vedula +8
Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data decentralized. This is particula…
PREF: Predictability Regularized Neural Motion Fields
Liangchen Song, Xuan Gong, Benjamin Planche +5
Knowing the 3D motions in a dynamic scene is essential to many vision applications. Recent progress is mainly focused on estimating the activity of some specific elements like huma…
NeuLF: Efficient Novel View Synthesis with Neural 4D Light Field
Zhong Li, Liangchen Song, Celong Liu +2
In this paper, we present an efficient and robust deep learning solution for novel view synthesis of complex scenes. In our approach, a 3D scene is represented as a light field, i.…
Track to Detect and Segment: An Online Multi-Object Tracker
Jialian Wu, Jiale Cao, Liangchen Song +3
Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking. In this paper, we present a new online joint detection and t…
Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective
Helong Zhou, Liangchen Song, Jiajie Chen +4
Knowledge distillation is an effective approach to leverage a well-trained network or an ensemble of them, named as the teacher, to guide the training of a student network. The out…
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation
Jialian Wu, Liangchen Song, Tiancai Wang +2
Despite the previous success of object analysis, detecting and segmenting a large number of object categories with a long-tailed data distribution remains a challenging problem and…
Unsupervised Domain Adaptive Re-Identification: Theory and Practice
Liangchen Song, Cheng Wang, Lefei Zhang +4
We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation. We first extend exist…