Object Reconstruction

72 papers with code • 0 benchmarks • 2 datasets

This task has no description! Would you like to contribute one?

TripoSR: Fast 3D Object Reconstruction from a Single Image

vast-ai-research/triposr 4 Mar 2024

This technical report introduces TripoSR, a 3D reconstruction model leveraging transformer architecture for fast feed-forward 3D generation, producing 3D mesh from a single image in under 0. 5 seconds.

3,275
04 Mar 2024

FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO and fast segment anything

safouaneelg/FusionVision 29 Feb 2024

Therefore, this paper introduces FusionVision, an exhaustive pipeline adapted for the robust 3D segmentation of objects in RGB-D imagery.

16
29 Feb 2024

iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views

chinhsuanwu/ifusion 28 Dec 2023

Our strategy unfolds in three steps: (1) We invert the diffusion model for camera pose estimation instead of synthesizing novel views.

68
28 Dec 2023

Splatter Image: Ultra-Fast Single-View 3D Reconstruction

szymanowiczs/splatter-image 20 Dec 2023

We introduce the Splatter Image, an ultra-fast approach for monocular 3D object reconstruction which operates at 38 FPS.

615
20 Dec 2023

Ins-HOI: Instance Aware Human-Object Interactions Recovery

jiajunzhang16/ins-hoi 15 Dec 2023

To address this, we further propose a complementary training strategy that leverages synthetic data to introduce instance-level shape priors, enabling the disentanglement of occupancy fields for different instances.

9
15 Dec 2023

HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video

zc-alexfan/hold 30 Nov 2023

Since humans interact with diverse objects every day, the holistic 3D capture of these interactions is important to understand and model human behaviour.

68
30 Nov 2023

HandNeRF: Learning to Reconstruct Hand-Object Interaction Scene from a Single RGB Image

samsunglabs/handnerf 14 Sep 2023

The inference as well as training-data generation for 3D hand-object scene reconstruction is challenging due to the depth ambiguity of a single image and occlusions by the hand and object.

39
14 Sep 2023

ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces

qianyiwu/objectsdf_plus ICCV 2023

Unlike traditional multi-view stereo approaches, the neural implicit surface-based methods leverage neural networks to represent 3D scenes as signed distance functions (SDFs).

135
15 Aug 2023

A One Stop 3D Target Reconstruction and multilevel Segmentation Method

ganlab/ostra 14 Aug 2023

We extend object tracking and 3D reconstruction algorithms to support continuous segmentation labels to leverage the advances in the 2D image segmentation, especially the Segment-Anything Model (SAM) which uses the pretrained neural network without additional training for new scenes, for 3D object segmentation.

13
14 Aug 2023

Contact-conditioned hand-held object reconstruction from single-view images

2023-MindSpore-4/Code12 journal 2023

Reconstructing the shape of hand-held objects from single-view color images is a long-standing problem in computer vision and computer graphics.

0
01 Aug 2023