A survey on segment anything model (sam): Vision foundation model meets prompt engineering
Segment anything model (SAM) developed by Meta AI Research has recently attracted
significant attention. Trained on a large segmentation dataset of over 1 billion masks, SAM is …
significant attention. Trained on a large segmentation dataset of over 1 billion masks, SAM is …
3d paintbrush: Local stylization of 3d shapes with cascaded score distillation
We present 3D Paintbrush a technique for automatically texturing local semantic regions on
meshes via text descriptions. Our method is designed to operate directly on meshes …
meshes via text descriptions. Our method is designed to operate directly on meshes …
Satr: Zero-shot semantic segmentation of 3d shapes
A Abdelreheem, I Skorokhodov… - Proceedings of the …, 2023 - openaccess.thecvf.com
We explore the task of zero-shot semantic segmentation of 3D shapes by using large-scale
off-the-shelf 2D im-age recognition models. Surprisingly, we find that modern zero-shot 2D …
off-the-shelf 2D im-age recognition models. Surprisingly, we find that modern zero-shot 2D …
Diffusion 3d features (diff3f): Decorating untextured shapes with distilled semantic features
NS Dutt, S Muralikrishnan… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
We present Diff3F as a simple robust and class-agnostic feature descriptor that can be
computed for untextured input shapes (meshes or point clouds). Our method distills diffusion …
computed for untextured input shapes (meshes or point clouds). Our method distills diffusion …
Scanents3d: Exploiting phrase-to-3d-object correspondences for improved visio-linguistic models in 3d scenes
The two popular datasets ScanRefer [20] and ReferIt3D [5] connect natural language to real-
world 3D scenes. In this paper, we curate a complementary dataset extending both the …
world 3D scenes. In this paper, we curate a complementary dataset extending both the …
NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs
Abstract A Neural Radiance Field (NeRF) encodes the specific relation of 3D geometry and
appearance of a scene. We here ask the question whether we can transfer the appearance …
appearance of a scene. We here ask the question whether we can transfer the appearance …
Neural semantic surface maps
We present an automated technique for computing a map between two genus‐zero shapes,
which matches semantically corresponding regions to one another. Lack of annotated data …
which matches semantically corresponding regions to one another. Lack of annotated data …
QAGait: Revisit Gait Recognition from a Quality Perspective
Gait recognition is a promising biometric method that aims to identify pedestrians from their
unique walking patterns. Silhouette modality, renowned for its easy acquisition, simple …
unique walking patterns. Silhouette modality, renowned for its easy acquisition, simple …
Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features
With the immense growth of dataset sizes and computing resources in recent years so-
called foundation models have become popular in NLP and vision tasks. In this work we …
called foundation models have become popular in NLP and vision tasks. In this work we …
Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases
R Aguina-Kang, M Gumin, DH Han, S Morris… - arXiv preprint arXiv …, 2024 - arxiv.org
We present a system for generating indoor scenes in response to text prompts. The prompts
are not limited to a fixed vocabulary of scene descriptions, and the objects in generated …
are not limited to a fixed vocabulary of scene descriptions, and the objects in generated …