SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.04352 · ICCV · 2023

3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment

Qing Li, Siyuan Huang, Yixin Chen, Xiaojian Ma, Ziyu Zhu, Zhidong Deng

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
3d-vista/3D-VisTA — 4 of 6
FunctionStatusWhere it lives
Registry Ran 3d-vista/3D-VisTA/model/vision/unified_encoder.py
code served (permissive licence) · get_code("af392075ecc51271")
TransformerEncoderLayer Ran 3d-vista/3D-VisTA/model/vision/unified_encoder.py
code served (permissive licence) · get_code("8f3dbe47a6eb7b40")
generate_causal_mask Ran 3d-vista/3D-VisTA/model/vision/unified_encoder.py
code served (permissive licence) · get_code("ef7878a2c111e5e2")
generate_mm_casual_mask Ran 3d-vista/3D-VisTA/model/vision/unified_encoder.py
code served (permissive licence) · get_code("e4b5ceca275ea601")
UnifiedSpatialCrossEncoderV2 Not yet run 3d-vista/3D-VisTA/model/vision/unified_encoder.py
code served (permissive licence) · get_code("5a6f1742cb13f1fc")
init_weights Not yet run 3d-vista/3D-VisTA/model/vision/unified_encoder.py
code served (permissive licence) · get_code("6c816339122f69e9")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

3D vision-language grounding (3D-VL) is an emerging field that aims to connect the 3D physical world with natural language, which is crucial for achieving embodied intelligence. Current 3D-VL models rely heavily on sophisticated modules, auxiliary losses, and optimization tricks, which calls for a simple and unified model. In this paper, we propose 3D-VisTA, a pre-trained Transformer for 3D Vision and Text Alignment that can be easily adapted to various downstream tasks. 3D-VisTA simply utilizes self-attention layers for both single-modal modeling and multi-modal fusion without any sophisticated task-specific design. To further enhance its performance on 3D-VL tasks, we construct ScanScribe, the first large-scale 3D scene-text pairs dataset for 3D-VL pre-training. ScanScribe contains 2,995 RGB-D scans for 1,185 unique indoor scenes originating from ScanNet and 3R-Scan datasets, along with paired 278K scene descriptions generated from existing 3D-VL tasks, templates, and GPT-3. 3D-VisTA is pre-trained on ScanScribe via masked language/object modeling and scene-text matching. It achieves state-of-the-art results on various 3D-VL tasks, ranging from visual grounding and dense captioning to question answering and situated reasoning. Moreover, 3D-VisTA demonstrates superior data efficiency, obtaining strong performance even with limited annotations during downstream task fine-tuning.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2308.04352")
get_code_for_paper("2308.04352")
have("2308.04352")

Connect an agent — have() is free.