Few-shot point cloud semantic segmentation aims to train a model to quic...
Existing fully-supervised point cloud segmentation methods suffer in the...
Event cameras offer many advantages over standard cameras due to their
d...
In this paper, we tackle the challenging task of learning a generalizabl...
Domain adaptation (DA) aims to transfer knowledge from a fully labeled s...
Although Neural Radiance Fields (NeRF) is popular in the computer vision...
The main challenges of 3D pose transfer are: 1) Lack of paired training ...
Remarkable progress has been made in 3D reconstruction from single-view ...
Dynamic neural radiance fields (dynamic NeRFs) have demonstrated impress...
Real-world data tends to follow a long-tailed distribution, where the cl...
Neural Radiance Fields (NeRF) has demonstrated remarkable 3D reconstruct...
The text-driven image and video diffusion models have achieved unprecede...
Direct mesh fitting for 3D hand shape reconstruction is highly accurate....
Animal pose estimation is an important but under-explored task due to th...
Recent works such as BARF and GARF can bundle adjust camera poses with n...
Dynamic Neural Radiance Field (NeRF) is a powerful algorithm capable of
...
Although many recent works have investigated generalizable NeRF-based no...
Despite the impressive results achieved by many existing Structure from
...
Recent neural radiance field (NeRF) representation has achieved great su...
Domain shift widely exists in the visual world, while modern deep neural...
Existing state-of-the-art method for audio-visual conditioned video
pred...
Semantic segmentation in 3D indoor scenes has achieved remarkable perfor...
Open world object detection aims at detecting objects that are absent in...
Explicit neural surface representations allow for exact and efficient
ex...
Current supervised cross-domain image retrieval methods can achieve exce...
Since Intersection-over-Union (IoU) based optimization maintains the
con...
In this paper, we consider the problem of domain generalization in seman...
Recent works on unsupervised domain adaptation (UDA) focus on the select...
Content-based Video Retrieval (CBVR) is used on media-sharing platforms ...
Incremental few-shot object detection aims at detecting novel classes wi...
In this paper, we study the task of synthetic-to-real domain generalized...
Despite recent success in incorporating learning into point cloud
regist...
State-of-the-art approaches for 6D object pose estimation require large
...
Deep learning-based approaches have shown remarkable performance in the ...
We introduce a new setting of Novel Class Discovery in Semantic Segmenta...
The environment of most real-world scenarios such as malls and supermark...
Most existing animal pose and shape estimation approaches reconstruct an...
Transformation Synchronization is the problem of recovering absolute
tra...
Deep networks have shown remarkable results in the task of object detect...
Deep learning technique has yielded significant improvements in point cl...
In this work, we introduce a new concept, named source-free open compoun...
Steerable CNN imposes the prior knowledge of transformation invariance o...
This paper presents DeepI2P: a novel approach for cross-modality registr...
Bottom-up approaches for image-based multi-person pose estimation consis...
Existing approaches for multi-view multi-person 3D pose estimation expli...
In this paper, we propose MINE to perform novel view synthesis and depth...
Animal pose estimation is an important field that has received increasin...
We propose a method for detecting structural changes in a city using ima...
Point clouds are often sparse and incomplete, which imposes difficulties...
3D human pose estimation from a single image is an inverse problem due t...