REVIEW 4 cited by
Scalable 3D Captioning with Pretrained Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We introduce Cap3D, an automatic approach for generating descriptive text for 3D objects. This approach utilizes pretrained models from image captioning, image-text alignment, and LLM to consolidate captions from multiple views of a 3D asset, completely side-stepping the time-consuming and costly process of manual annotation. We apply Cap3D to the recently introduced large-scale 3D dataset, Objaverse, resulting in 660k 3D-text pairs. Our evaluation, conducted using 41k human annotations from the same dataset, demonstrates that Cap3D surpasses human-authored descriptions in terms of quality, cost, and speed. Through effective prompt engineering, Cap3D rivals human performance in generating geometric descriptions on 17k collected annotations from the ABO dataset. Finally, we finetune Text-to-3D models on Cap3D and human captions, and show Cap3D outperforms; and benchmark the SOTA including Point-E, Shape-E, and DreamFusion.
Forward citations
Cited by 4 Pith papers
-
From Geometric Labels to Semantic Understanding of Indoor Building Components Using Multimodal Large Language Models
Building-MLLM, with PIE, GPR, fixed prefix and multi-dimensional LoRA plus a 37k-pair synthetic dataset, reaches 88/65/68 % on recognition, captioning and multi-engineering QA for 47 indoor component categories.
-
PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation
PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.
-
Few-step Flow for 3D Generation via Marginal-Data Transport Distillation
MDT-dist distills a pretrained 3D flow model into a 1-2 step generator using velocity matching plus velocity distillation, cutting TRELLIS inference from 6.1s to 0.68s while approximately preserving generation quality.
-
CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation
CoNav lets a frozen 3D-text model pass spatial text hints to a lightly fine-tuned image-text navigation agent, improving path efficiency on several VLN benchmarks, though not all claimed state-of-the-art results hold.
Discussion (0). Continue with ORCID to comment.