21 citations · 26 across the 9 of their papers we have counts for
11 papers
Diffusion-guided Generalizable Enhancer for Urban Scene Reconstruction
Henry Che, Jingkang Wang, Yun Chen +3
Urban scene reconstruction from real-world observations has emerged as a powerful tool for self-driving development and testing. While current neural rendering approaches achieve h…
GenAssets: Generating in-the-wild 3D Assets in Latent Space
Ze Yang, Jingkang Wang, Haowei Zhang +3
High-quality 3D assets for traffic participants are critical for multi-sensor simulation, which is essential for the safe end-to-end development of autonomy. Building assets from i…
Flux4D: Flow-based Unsupervised 4D Reconstruction
Jingkang Wang, Henry Che, Yun Chen +4
Reconstructing large-scale dynamic scenes from visual observations is a fundamental challenge in computer vision, with critical implications for robotics and autonomous systems. Wh…
SaLF: Sparse Local Fields for Multi-Sensor Rendering in Real-Time
Yun Chen, Matthew Haines, Jingkang Wang +5
High-fidelity sensor simulation of light-based sensors such as cameras and LiDARs is critical for safe and accurate autonomy testing. Neural radiance field (NeRF)-based methods tha…
G3R: Gradient Guided Generalizable Reconstruction
Yun Chen, Jingkang Wang, Ze Yang +2
Large scale 3D scene reconstruction is important for applications such as virtual reality and simulation. Existing neural rendering approaches (e.g., NeRF, 3DGS) have achieved real…
LightSim: Neural Lighting Simulation for Urban Scenes
Ava Pun, Gary Sun, Jingkang Wang +5
Different outdoor illumination conditions drastically alter the appearance of urban scenes, and they can harm the performance of image-based robot perception systems if not seen du…
Real-Time Neural Rasterization for Large Scenes
Jeffrey Yunfan Liu, Yun Chen, Ze Yang +3
We propose a new method for realistic real-time novel-view synthesis (NVS) of large scenes. Existing neural rendering methods generate realistic results, but primarily work for sma…
Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulation
Jay Sarva, Jingkang Wang, James Tu +3
Self-driving vehicles (SDVs) must be rigorously tested on a wide range of scenarios to ensure safe deployment. The industry typically relies on closed-loop simulation to evaluate h…
Just Label What You Need: Fine-Grained Active Selection for Perception and Prediction through Partially Labeled Scenes
Sean Segal, Nishanth Kumar, Sergio Casas +4
Self-driving vehicles must perceive and predict the future positions of nearby actors in order to avoid collisions and drive safely. A learned deep learning module is often respons…
Adversarial Attack Generation Empowered by Min-Max Optimization
Jingkang Wang, Tianyun Zhang, Sijia Liu +4
The worst-case training principle that minimizes the maximal adversarial loss, also known as adversarial training (AT), has shown to be a state-of-the-art approach for enhancing ad…
The Helmholtz Method: Using Perceptual Compression to Reduce Machine Learning Complexity
Gerald Friedland, Jingkang Wang, Ruoxi Jia +1
This paper proposes a fundamental answer to a frequently asked question in multimedia computing and machine learning: Do artifacts from perceptual compression contribute to error i…