Search Results for author: Junpeng Jing

Found 6 papers, 2 papers with code

Hypo3D: Exploring Hypothetical Reasoning in 3D

no code implementations2 Feb 2025 Ye Mao, Weixun Luo, Junpeng Jing, Anlan Qiu, Krystian Mikolajczyk

The rise of vision-language foundation models marks an advancement in bridging the gap between human and machine capabilities in 3D scene reasoning.

Question Answering Visual Question Answering

Match Stereo Videos via Bidirectional Alignment

no code implementations30 Sep 2024 Junpeng Jing, Ye Mao, Anlan Qiu, Krystian Mikolajczyk

Regarding datasets, current synthetic object-based and indoor datasets are commonly used for training and benchmarking, with a lack of outdoor nature scenarios.

Benchmarking Stereo Matching

OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images

1 code implementation25 Apr 2024 Ye Mao, Junpeng Jing, Krystian Mikolajczyk

In this paper, we present OpenDlign, a novel open-world 3D model using depth-aligned images generated from a diffusion model for robust multimodal alignment.

Representation Learning Transfer Learning +4

Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching

no code implementations16 Mar 2024 Junpeng Jing, Ye Mao, Krystian Mikolajczyk

Towards this challenge, we develop a bidirectional alignment mechanism for adjacent frames as a fundamental operation.

Stereo Matching

Cannot find the paper you are looking for? You can Submit a new open access paper.