On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “text-to-3D”

DreamPropeller: Supercharge Text-to-3D Generation with Parallel Samplingcs.CV

DreamPropeller accelerates text-to-3D generation by 4.7x with minimal loss in quality.

problem Long generation times in text-to-3D generation algorithms degrade user experience.

method DreamPropeller uses Picard iterations generalized for non-ODE paths to accelerate parallel sampling.

result Empirically achieves up to 4.7x speedup with negligible quality loss.

text-to-3D acceleration parallel sampling Picard iterations diffusion models

2023-11-28abs ↗pdf ↗

Variance Reduction for Expectations with Diffusion Teacherscs.LG

CARV reduces compute cost for downstream pipelines using diffusion models.

problem High variance in Monte Carlo estimators from diffusion models limits compute efficiency.

method CARV uses hierarchical MC estimation with amortized upstream computation and stratified-inverse-CDF.

result CARV delivers 2-3x effective compute multipliers without changing the objective.

diffusion models Monte Carlo variance reduction compute efficiency text-to-3D

2026-05-20abs ↗pdf ↗

DreamFusion: Text-to-3D using 2D Diffusioncs.CV

DreamFusion uses text-to-image diffusion models to create 3D images efficiently.

problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.

method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.

result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.

text-to-image diffusion models 3D synthesis NeRF probabilistic distillation

2022-09-29abs ↗pdf ↗