# Beyond Geometry: Artistic Disparity Synthesis for Immersive 2D-to-3D

arXiv: https://arxiv.org/abs/2603.05906 · HTML: https://mlsanity.com/paper/2603.05906/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 50 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [Inpaint Anything: Segment Anything Meets Image Inpainting](https://mlsanity.com/paper/2304.06790/) (2023)
- [SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow](https://mlsanity.com/paper/2405.14793/) (2024)
- [Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1604.03650/) (2016)
- [DiffuEraser: A Diffusion Model for Video Inpainting](https://mlsanity.com/paper/2501.10018/) (2025)
- [I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modeling](https://mlsanity.com/paper/2102.03725/) (2021)
- [StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos](https://mlsanity.com/paper/2409.07447/) (2024)
- [A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling](https://mlsanity.com/paper/2312.02719/) (2023)
- [SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving](https://mlsanity.com/paper/2512.10719/) (2025)
- [An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models](https://mlsanity.com/paper/2411.16308/) (2024)
- [Small Obstacle Avoidance Based on RGB-D Semantic Segmentation](https://mlsanity.com/paper/1908.11675/) (2019)
- [Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusion](https://mlsanity.com/paper/2508.03252/) (2025)
- [Deep Global-Relative Networks for End-to-End 6-DoF Visual Localization and Odometry](https://mlsanity.com/paper/1812.07869/) (2018)
- [M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversion](https://mlsanity.com/paper/2505.16565/) (2025)
- [SpatialMe: Stereo Video Conversion Using Depth-Warping and Blend-Inpainting](https://mlsanity.com/paper/2412.11512/) (2024)
- [RemedyGS: Defend 3D Gaussian Splatting against Computation Cost Attacks](https://mlsanity.com/paper/2511.22147/) (2025)
- [Optimizing for the Shortest Path in Denoising Diffusion Model](https://mlsanity.com/paper/2503.03265/) (2025)
- [Eye2Eye: A Simple Approach for Monocular-to-Stereo Video Synthesis](https://mlsanity.com/paper/2505.00135/) (2025)
- [A Unified Framework for Mutual Improvement of SLAM and Semantic Segmentation](https://mlsanity.com/paper/1812.10016/) (2018)
- [Token-level Data Selection for Safe LLM Fine-tuning](https://mlsanity.com/paper/2603.01185/) (2026)
- [Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images](https://mlsanity.com/paper/2104.06782/) (2021)
- [Learning Triangular Distribution in Visual World](https://mlsanity.com/paper/2311.18605/) (2023)

## Abstract (arXiv)

Current 2D-to-3D conversion methods achieve geometric accuracy but are artistically deficient, failing to replicate the immersive and emotionally resonant experience of professional 3D cinema. This is because geometric reconstruction paradigms mistake deliberate artistic intent, such as strategic zero-plane shifts for pop-out effects and local depth sculpting, for data noise or ambiguity. This paper argues for a new paradigm: Artistic Disparity Synthesis, shifting the goal from physically accurate disparity estimation to artistically coherent disparity synthesis. We propose Art3D, a preliminary framework exploring this paradigm. Art3D uses a dual-path architecture to decouple global depth parameters (macro-intent) from local artistic effects (visual brushstrokes) and learns from professional 3D film data via indirect supervision. We also introduce a preliminary evaluation method to quantify cinematic alignment. Experiments show our approach demonstrates potential in replicating key local out-of-screen effects and aligning with the global depth styles of cinematic 3D content, laying the groundwork for a new class of artistically-driven conversion tools.