AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

ConRad: Image Constrained Radiance Fields for 3D Generation from a Single Image

Senthil Purushwalkam, Nikhil Naik

NeurIPS 2023 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use ConRad instead of RealFusionConRad · ShapeNet all viewsCLIP distance d_oracle (lower better): 0.460 -> 0.273Improved
use ConRad instead of NeuralLift-360ConRad · ShapeNet near referenceCLIP distance d_ref (lower better): 0.543 -> 0.286Improved
use ConRad instead of PointEConRad · ShapeNet all viewsCLIP distance d_all (lower better): 0.482 -> 0.316Improved
remove warm start (ablation)ConRad · qualitative examples3D structure crispnessMixed
remove depth loss (ablation)ConRad · qualitative examples3D structure correctness and computeMixed
remove textual inversion (ablation)ConRad · qualitative examplesview-consistent appearanceHurt
remove color constraint (ablation)ConRad · qualitative examplesrealism and fidelityHurt
remove both color and density constraints, keeping depth loss (ablation)ConRad · qualitative examplesrealismHurt
use ConRad on one object where baselines winConRad · ShapeNet table bdd12e, d_refCLIP distance: 0.380 -> 0.560Hurt
use ConRad on car object 1abecaConRad · ShapeNet car 1abeca, d_refCLIP distance: 0.458 -> 0.469Hurt
use textual inversion embedding to mitigate saturated colors from Stable Diffusion (ablation)ConRad · failure casescolor fidelityMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy