Search Results for author:
Found 9 papers, 4 papers with code
Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding
In this paper, we propose Geometry Enhanced Masked Image Modeling (GeoMIM) to transfer the knowledge of the LiDAR model in a pretrain-finetune paradigm for improving the multi-view camera-based 3D detection.
Towards Smooth Video Composition
Video generation requires synthesizing consistent and persistent frames with dynamic content over time.
Ranked #1 on
Video Generation
on YouTube Driving
Noise-resilient approach for deep tomographic imaging
We propose a noise-resilient deep reconstruction algorithm for X-ray tomography.
Generative Category-Level Shape and Pose Estimation with Semantic Primitives
Then, by using a SIM(3)-invariant shape descriptor, we gracefully decouple the shape and pose of an object, thus supporting latent shape optimization of target objects in arbitrary poses.
Ranked #1 on
6D Pose Estimation using RGBD
on REAL275
F3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks
Formulated as a conditional generation problem, face animation aims at synthesizing continuous face images from a single source image driven by a set of conditional face motion.
Extracting particle size distribution from laser speckle with a physics-enhanced autocorrelation-based estimator (PEACE)
Extracting quantitative information about highly scattering surfaces from an imaging system is challenging because the phase of the scattered light undergoes multiple folds upon propagation, resulting in complex speckle patterns.
Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining
Specifically, we train an inverse dynamic model with a small amount of labeled data and use it to predict action labels for all the YouTube video frames.
MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning
Based on MetaDrive, we construct a variety of RL tasks and baselines in both single-agent and multi-agent settings, including benchmarking generalizability across unseen scenes, safe exploration, and learning multi-agent traffic.
Improving the Generalization of End-to-End Driving through Procedural Generation
We validate that training with the increasing number of procedurally generated scenes significantly improves the generalization of the agent across scenarios of different traffic densities and road networks.
