AI Paper Atlas

Research map / 3D vision / 3D generation

InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalization

Daniel Gilo, Or Litany

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 1 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
distill teacher edits into multi-view student instead of student only (ablation)I-Mix2Mix · Ablation, 6 editsCLIP Directional Consistency: 0.014 -> 0.337Improved
add multi-view student to teacher-only per-view editing (ablation)I-Mix2Mix · Ablation, 6 editsCLIP Directional Consistency: 0.228 -> 0.337Improved
edit the reference frame with the teacher before initialization (ablation)I-Mix2Mix · Ablation, 6 editsCLIP Directional Consistency: 0.326 -> 0.337Improved
replace bilinear alignment with a learned conv mapping (ablation)I-Mix2Mix · Ablation, 6 editsCLIP Directional Consistency: 0.337 -> 0.287No clear effect
use stochastic truncated-normal teacher timestep instead of uniform t (ablation)I-Mix2Mix · Ablation, 6 editsCLIP Directional Similarity: 0.146 -> 0.178Improved
use stochastic truncated-normal teacher timestep instead of student-matched t (ablation)I-Mix2Mix · Ablation, 6 editsCLIP Directional Similarity: 0.107 -> 0.178Improved
add Random Cross-View Attention in teacher (ablation)I-Mix2Mix · Ablation, 6 editsCLIP Directional Consistency: 0.230 -> 0.337Improved
add I-Mix2Mix versus DGEmulti-view editing · Sparse-view editing, N=4, 20 edits on 3 I-N2N scenesCLIP Directional Consistency: 0.287 -> 0.342Improved
add I-Mix2Mix versus DGEmulti-view editing · Sparse-view editing, N=4, 20 edits on 3 I-N2N scenesCLIP Directional Similarity: 0.182 -> 0.173Hurt
replace single-step student prediction with three-step alternative (ablation)I-Mix2Mix · N=4 peak GPU memorymemoryHurt
use latent interpolation instead of decoder-encoder alignment (ablation)I-Mix2Mix · peak GPU memorymemoryImproved
fine-tune student with LoRA instead of full U-Net (ablation)I-Mix2Mix · editingqualityHurt

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