Feat2GS: Probing Visual Foundation Models with Gaussian Splatting

• URL: http://arxiv.org/abs/2412.09606v1
• Date: Thu, 12 Dec 2024 18:59:28 GMT
• Title: Feat2GS: Probing Visual Foundation Models with Gaussian Splatting
• Authors: Yue Chen, Xingyu Chen, Anpei Chen, Gerard Pons-Moll, Yuliang Xiu,
• Abstract summary: Visual foundation models (VFMs) are trained on extensive datasets but often limited to 2D images. We introduce Feat2GS, which readout 3D Gaussians attributes from VFM features extracted from unposed images. We conduct extensive experiments to probe the 3D awareness of several VFMs, and investigate the ingredients that lead to a 3D aware VFM.
• Score: 53.86049874165888
• License:
• Abstract: Given that visual foundation models (VFMs) are trained on extensive datasets but often limited to 2D images, a natural question arises: how well do they understand the 3D world? With the differences in architecture and training protocols (i.e., objectives, proxy tasks), a unified framework to fairly and comprehensively probe their 3D awareness is urgently needed. Existing works on 3D probing suggest single-view 2.5D estimation (e.g., depth and normal) or two-view sparse 2D correspondence (e.g., matching and tracking). Unfortunately, these tasks ignore texture awareness, and require 3D data as ground-truth, which limits the scale and diversity of their evaluation set. To address these issues, we introduce Feat2GS, which readout 3D Gaussians attributes from VFM features extracted from unposed images. This allows us to probe 3D awareness for geometry and texture via novel view synthesis, without requiring 3D data. Additionally, the disentanglement of 3DGS parameters - geometry ($\boldsymbol{x}, \alpha, \Sigma$) and texture ($\boldsymbol{c}$) - enables separate analysis of texture and geometry awareness. Under Feat2GS, we conduct extensive experiments to probe the 3D awareness of several VFMs, and investigate the ingredients that lead to a 3D aware VFM. Building on these findings, we develop several variants that achieve state-of-the-art across diverse datasets. This makes Feat2GS useful for probing VFMs, and as a simple-yet-effective baseline for novel-view synthesis. Code and data will be made available at https://fanegg.github.io/Feat2GS/.

Related papers

• ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images [47.682942867405224]
  ConDense is a framework for 3D pre-training utilizing existing 2D networks and large-scale multi-view datasets. We propose a novel 2D-3D joint training scheme to extract co-embedded 2D and 3D features in an end-to-end pipeline.
  arXiv  Detail & Related papers  (2024-08-30T05:57:01Z)
• Probing the 3D Awareness of Visual Foundation Models [56.68380136809413]
  We analyze the 3D awareness of visual foundation models. We conduct experiments using task-specific probes and zero-shot inference procedures on frozen features.
  arXiv  Detail & Related papers  (2024-04-12T17:58:04Z)
• Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding [23.672405624011873]
  We propose a module to consolidate the 3D visual stream by 2D clues synthesized from point clouds. We empirically show their aptitude to boost the quality of the learned visual representations. Our proposed module, dubbed as Look Around and Refer (LAR), significantly outperforms the state-of-the-art 3D visual grounding techniques on three benchmarks.
  arXiv  Detail & Related papers  (2022-11-25T17:12:08Z)
• Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer? [111.11502241431286]
  Vision Transformers (ViTs) have proven to be effective in solving 2D image understanding tasks. ViTs for 2D and 3D tasks have so far adopted vastly different architecture designs that are hardly transferable. This paper demonstrates the appealing promise to understand the 3D visual world, using a standard 2D ViT architecture.
  arXiv  Detail & Related papers  (2022-09-15T03:34:58Z)
• Gait Recognition in the Wild with Dense 3D Representations and A Benchmark [86.68648536257588]
  Existing studies for gait recognition are dominated by 2D representations like the silhouette or skeleton of the human body in constrained scenes. This paper aims to explore dense 3D representations for gait recognition in the wild. We build the first large-scale 3D representation-based gait recognition dataset, named Gait3D.
  arXiv  Detail & Related papers  (2022-04-06T03:54:06Z)
• FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection [78.00922683083776]
  It is non-trivial to make a general adapted 2D detector work in this 3D task. In this technical report, we study this problem with a practice built on fully convolutional single-stage detector. Our solution achieves 1st place out of all the vision-only methods in the nuScenes 3D detection challenge of NeurIPS 2020.
  arXiv  Detail & Related papers  (2021-04-22T09:35:35Z)
• 3D-to-2D Distillation for Indoor Scene Parsing [78.36781565047656]
  We present a new approach that enables us to leverage 3D features extracted from large-scale 3D data repository to enhance 2D features extracted from RGB images. First, we distill 3D knowledge from a pretrained 3D network to supervise a 2D network to learn simulated 3D features from 2D features during the training. Second, we design a two-stage dimension normalization scheme to calibrate the 2D and 3D features for better integration. Third, we design a semantic-aware adversarial training model to extend our framework for training with unpaired 3D data.
  arXiv  Detail & Related papers  (2021-04-06T02:22:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.