An outlook into the future of egocentric vision
What will the future be? We wonder! In this survey, we explore the gap between current
research in egocentric vision and the ever-anticipated future, where wearable computing …
research in egocentric vision and the ever-anticipated future, where wearable computing …
Complete-to-partial 4D distillation for self-supervised point cloud sequence representation learning
Recent work on 4D point cloud sequences has attracted a lot of attention. However,
obtaining exhaustively labeled 4D datasets is often very expensive and laborious, so it is …
obtaining exhaustively labeled 4D datasets is often very expensive and laborious, so it is …
Shapellm: Universal 3d object understanding for embodied interaction
This paper presents ShapeLLM, the first 3D Multimodal Large Language Model (LLM)
designed for embodied interaction, exploring a universal 3D object understanding with 3D …
designed for embodied interaction, exploring a universal 3D object understanding with 3D …
LeaF: Learning Frames for 4D Point Cloud Sequence Understanding
We focus on learning descriptive geometry and motion features from 4D point cloud
sequences in this work. Existing works usually develop generic 4D learning tools without …
sequences in this work. Existing works usually develop generic 4D learning tools without …
Pointcmp: Contrastive mask prediction for self-supervised learning on point cloud videos
Self-supervised learning can extract representations of good quality from solely unlabeled
data, which is appealing for point cloud videos due to their high labelling cost. In this paper …
data, which is appealing for point cloud videos due to their high labelling cost. In this paper …
Masked spatio-temporal structure prediction for self-supervised learning on point cloud videos
Recently, the community has made tremendous progress in developing effective methods
for point cloud video understanding that learn from massive amounts of labeled data …
for point cloud video understanding that learn from massive amounts of labeled data …
Point contrastive prediction with semantic clustering for self-supervised learning on point cloud videos
We propose a unified point cloud video self-supervised learning framework for object-centric
and scene-centric data. Previous methods commonly conduct representation learning at the …
and scene-centric data. Previous methods commonly conduct representation learning at the …
Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence
We study a new problem of semantic complete scene forecasting (SCSF) in this work. Given
a 4D dynamic point cloud sequence, our goal is to forecast the complete scene …
a 4D dynamic point cloud sequence, our goal is to forecast the complete scene …
Contrastive predictive autoencoders for dynamic point cloud self-supervised learning
We present a new self-supervised paradigm on point cloud sequence understanding.
Inspired by the discriminative and generative self-supervised methods, we design two tasks …
Inspired by the discriminative and generative self-supervised methods, we design two tasks …
Interactive humanoid: Online full-body motion reaction synthesis with social affordance canonicalization and forecasting
We focus on the human-humanoid interaction task optionally with an object. We propose a
new task named online full-body motion reaction synthesis, which generates humanoid …
new task named online full-body motion reaction synthesis, which generates humanoid …