Spaces:
Running on Zero
Running on Zero
|
Download README.md from pradhaansbhat/Thinking-In-Boxes: direct link, hf CLI and curl.
- Browser
- Download file 4.38 kB
-
https://huggingface.co/spaces/pradhaansbhat/Thinking-In-Boxes/resolve/main/README.md
- Command line
-
hf download hf://spaces/pradhaansbhat/Thinking-In-Boxes/README.md
-
curl -L -o README.md https://huggingface.co/spaces/pradhaansbhat/Thinking-In-Boxes/resolve/main/README.md
4.38 kB
| title: Thinking in Boxes | |
| emoji: 📦 | |
| colorFrom: red | |
| colorTo: gray | |
| sdk: gradio | |
| sdk_version: 6.30.0 | |
| app_file: demo.py | |
| pinned: false | |
| short_description: 3D Editing in Real Images Made Easy (NeurIPS 2026) | |
| <div align="center"> | |
| # Thinking in Boxes: 3D Editing in Real Images Made Easy | |
| ### NeurIPS 2026 | |
| [**Pradhaan S Bhat**](https://pradhaansbhat.github.io/)<sup>1</sup><sup>∗</sup> · [**Naveen Chandra R**](https://www.linkedin.com/in/naveen-chandra-r-7230aa192)<sup>1</sup><sup>∗</sup> · [**Rishubh Parihar**](https://rishubhpar.github.io/)<sup>1</sup> · [**Vaibhav Vavilala**](https://www.linkedin.com/in/vaibhav-vavilala)<sup>2</sup> · [**R. Venkatesh Babu**](https://cds.iisc.ac.in/faculty/venky/)<sup>1</sup> · [**D. A. Forsyth**](http://luthuli.cs.uiuc.edu/~daf/)<sup>3</sup> · [**Anand Bhattad**](https://anandbhattad.github.io/)<sup>4</sup> | |
| <sup>1</sup> Indian Institute of Science · <sup>2</sup> Apple · <sup>3</sup> UIUC · <sup>4</sup> Johns Hopkins University | |
| <sup>∗</sup> Equal Contribution | |
| [](https://arxiv.org/abs/2606.20556) | |
| [](https://thinking-in-boxes.github.io) | |
| [](https://huggingface.co/pradhaansbhat/Thinking-In-Boxes) | |
| [](https://huggingface.co/datasets/pradhaansbhat/Thinking-In-Boxes) | |
| [](https://github.com/PradhaanSBhat/Thinking-In-Boxes) | |
| </div> | |
| --- | |
| ## 📚 Abstract | |
| Text and 2D-conditioning interfaces provide weak, ambiguous control over spatial | |
| transformations in image editing — particularly under large object motions and | |
| camera changes. Prior work has used 3D primitives such as boxes, but only as loose | |
| conditioning signals indicating approximate object location rather than specifying | |
| the transformation. | |
| We instead use **3D boxes as structured specifications**: the user provides the input | |
| and output boxes of the edit, casting editing as a well-posed geometry problem. This | |
| "thinking in boxes" interface, where each box face is color-coded to convey 3D | |
| orientation, gives precise control over translation, rotation, scaling, and viewpoint | |
| changes in real images while preserving scene and object identity, and recovering | |
| previously unseen object regions. To ground transformations in scene appearance, we | |
| introduce a **depth-aligned planar floor** as a global reference frame, shaded with | |
| depth-aware cues. | |
| Conditioned on this structure, an image generator produces consistent results under | |
| large transformations. Trained in two stages — on synthetic multi-object scenes and a | |
| small set of real-world videos from Objectron — the system generalizes to complex, | |
| in-the-wild real images. Our method operates directly on real photographs and | |
| substantially **outperforms recent state-of-the-art methods** on large 3D edits. | |
| --- | |
| # Demo Usage | |
| Interactive demo for **[NeurIPS'26] Thinking in Boxes: 3D Editing in Real Images Made Easy**. | |
| - Fit 3D boxes to objects, set a **source** pose, bookmark it on the left rail, edit to a **target** pose, then generate. | |
| - Read the tooltips and hover over icons for details on how to use the 3D Editor. | |
| - Runs on **ZeroGPU** (free, time-sliced RTX PRO 6000). Generation consumes your daily GPU quota. | |
| - 3D auto-detection runs in **mock** mode on the Space (the full WildDet3D detector needs a | |
| dedicated GPU/deps). Place and refine 3D boxes by hand. (See the [GitHub Repository](https://github.com/PradhaanSBhat/Thinking-In-Boxes) to use WildDet3D) | |
| ## Setup notes (for whoever deploys this Space) | |
| 1. **Hardware:** Settings → Hardware → **ZeroGPU**. | |
| 2. **Secret:** add `HF_TOKEN` from an account that has accepted the | |
| [FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev) license — | |
| the base model is gated and won't download otherwise. | |
| 3. **Files in the Space repo:** `assets/` `demo.py`, `box-editor.html`, | |
| `pipelines/pipeline_flux_kontext.py` (the custom pipeline), and `requirements.txt`. | |
| 4. The default model + LoRA download on first boot (slow once, cached after). | |