**Matheus Gadelha** ![ ](fig/me.jpg width="25%") I am currently a Research Scientist at [Adobe Research](https://research.adobe.com/). I received my PhD from [University of Massachusetts - Amherst](https://www.cics.umass.edu/) while being supervised by [Prof. Rui Wang](https://people.cs.umass.edu/~ruiwang/) and [Prof. Subhransu Maji](http://people.cs.umass.edu/~smaji/). I am interested in Computer Graphics, Vision and their intersections with Machine Learning. My work is focused on models and representations of tridimensional data for both discriminative and generative models. Lately, I have been particularly interested in mechanisms to incorporate 3D capabilities into large generative models so we can properly control them and robustly create/understand 3D data. I am also broadly interested in techniques (not necessarily ML-based) that allow us to better manipulate and author 3D content. Latest on my research: * [Directing Image Generative Models.](directing_image_gen_models.html) **Internships for PhD students: ** If you are interested in related areas to the ones I've mentioned above (or anything related to my previous research), don't be shy and send me an e-mail with your CV and a short description of the problems you are interested in working on. We are always looking for talented interns to join us at Adobe Research. **Academic Collaborations: ** If you are a professor or a student interested in working with me, feel free to send me an e-mail -- I am more than happy to discuss interesting research problems we could work on together (or even just to chat about research). [[CV](cv.pdf)] [[twitter](https://twitter.com/gadelha_m)] [[email](mailto:matheusabrantesgadelha@gmail.com)] [[scholar](https://scholar.google.com/citations?user=VhqmvXsAAAAJ&hl=en)] (#) Work Experience ![ ](fig/adobe_logo.png width="7%") **Adobe**. Research Scientist at San Jose, CA. _June 2021 - Now_.
---------------------------------------------------------------------------------------------------- ![ ](fig/google_logo.png width="7%") **Google (Perception)**. Research Intern in ~~Mountain View, CA~~ Amherst, MA. _Summer 2020_.
---------------------------------------------------------------------------------------------------- ![ ](fig/adobe_logo.png width="7%") **Adobe**. Research Intern at San Jose, CA. _Summer 2019_.
---------------------------------------------------------------------------------------------------- ![ ](fig/amazon_logo.png width="7%") **Amazon**. Applied Scientist Intern at Pasadena, CA. _Summer 2018_.
(#) Research ![ ](fig/dmesh_teaser.gif width="20%") [arXiv] **DMesh: A Differentiable Representation for General Meshes** _Sanghyun Son, **Matheus Gadelha**, Yang Zhou, Zexiang Xu, Ming C. Lin, Yi Zhou_ [[Pre-print](https://www.cs.umd.edu/~shh1295/dmesh/full.pdf)] [[Project Page](https://sonsang.github.io/dmesh-project/)] ----- ![ ](fig/gem3d.gif width="20%") [SIGGRAPH 2024] **GEM3D: Generative Medial Abstractions for 3D Shape Synthesis** _Dmitry Petrov, Pradyumn Goyal, Vikas Thamizharasan, Vova Kim, **Matheus Gadelha**, Melinos Averkiou, Siddhartha Chaudhuri, Evangelos Kalogerakis_ [[Pre-print](https://arxiv.org/abs/2402.16994)] [[Project Page](https://lodurality.github.io/GEM3D/)] ----- ![ ](fig/c3dw.png width="20%") [CVPR 2024] **Learning Continuous 3D Words for Text-to-Image Generation** _Ta-Ying Cheng, **Matheus Gadelha**, Thibault Groueix, Matthew Fisher, Radomir Mech, Andrew Markham, Niki Trigoni_ [[Pre-print](https://ttchengab.github.io/continuous_3d_words/c3d_words.pdf)] [[Project Page](https://ttchengab.github.io/continuous_3d_words/)] ----- ![ ](fig/sunflower-gif.gif width="20%") [CVPR 2024] **Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D** _Karran Pandey, Paul Guerrero, **Matheus Gadelha**, Yannick Hold-Geoffroy, Karan Singh, Niloy Mitra_ [[Pre-print](https://arxiv.org/pdf/2312.02190.pdf)] [[Project Page](https://diffusionhandles.github.io/)] ----- ![ ](fig/genren.gif width="20%") [CVPR 2024] **Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models** _Shengqu Cai, Duygu Ceylan, **Matheus Gadelha**, Chun-Hao Huang, Tuanfeng Y. Wang, Gordon Wetzstein_ [[Pre-print](https://primecai.github.io/generative_rendering/assets/pdf/low_res.pdf)] [[Project Page](https://primecai.github.io/generative_rendering/index)] ----- ![ ](fig/3dminer.png width="20%") [ICCV 2023] **3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets** _Ta-Ying Cheng, **Matheus Gadelha**, Soren Pirk, Thibault Groueix, Radomir Mech, Andrew Markham, Niki Trigoni_ [[Paper](https://openaccess.thecvf.com/content/ICCV2023/html/Cheng_3DMiner_Discovering_Shapes_from_Large-Scale_Unannotated_Image_Datasets_ICCV_2023_paper.html)] [[Project Page](https://ttchengab.github.io/3dminerOfficial/)] ----- ![ ](fig/anise.png width="20%") [TVCG] **ANISE: Assembly-based Neural Implicit Surface rEconstruction** _Dmitry Petrov, **Matheus Gadelha**, Radomir Mech, Evangelos Kalogerakis_ [[Pre-print](https://arxiv.org/pdf/2205.13682.pdf)] [[Project Page](https://lodurality.github.io/ANISE/)] ----- ![ ](fig/turntables.png width="20%") [ICCV 2023 Workshop] **Accidental Turntables: Learning 3D Pose by Watching Objects Turn** _Zezhou Cheng, **Matheus Gadelha**, Subhransu Maji_ [[Pre-print](https://arxiv.org/pdf/2212.06300.pdf)] [[Project Page](https://people.cs.umass.edu/~zezhoucheng/acci-turn/)] ----- ![ ](fig/recovdetail.png width="20%") [ECCV 2022 Workshop] **Recovering Detail in 3D Shapes Using Disparity Maps** _Marissa Ramirez de Chanlatte, **Matheus Gadelha**, Thibault Groueix, Radomir Mech_ [[Pre-print](https://arxiv.org/pdf/2207.00182.pdf)] ----- ![ ](fig/surfit.png width="20%") [SGP 2022] **PrimFit: Learning to Fit Primitives Improves Few Shot Learning on Point Clouds** _Gopal Sharma, Bidya Dash, **Matheus Gadelha**, Aruni RoyChowdhury, Marios Loizou, Evangelos Kalogerakis, Liangliang Cao, Erik Learned-Miller, Rui Wang and Subhransu Maji_ [[Pre-print](https://arxiv.org/pdf/2112.13942.pdf)] ----- ![ ](fig/planar_recon.png width="20%") [CVPR 2022] **PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos** _Yiming Xie, **Matheus Gadelha**, Fengting Yang, Xiaowei Zhou, Huaizu Jiang_ [[Paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Xie_PlanarRecon_Real-Time_3D_Plane_Detection_and_Reconstruction_From_Posed_Monocular_CVPR_2022_paper.pdf)] [[Supplemental](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Xie_PlanarRecon_Real-Time_3D_CVPR_2022_supplemental.pdf)] ----- ![ ](fig/tmm_paper.png width="20%") [IEEE AIVR 2021] **Trace Match & Merge: Long-TermField-Of-View Prediction for AR Applications** _Adam Viola`*`, Sahil Sharma`*`,Pankaj Bishnoi`*`, **Matheus Gadelha**, Stefano Petrangeli, Haoliang Wang, Viswanathan Swaminathan_ **Best paper candidate at [IEEE AIVR](https://ieee-aivr.cs.nthu.edu.tw/program)**. [[Paper](AIVR_2021___AR_FOV_prediction.pdf)] ----- ![ ](fig/prgan_journal.png width="20%") [IJCV 2020] **Inferring 3D Shapes from Image Collections using Adversarial Networks** _**Matheus Gadelha**, Aartika Rai, Rui Wang, Subhransu Maji_ [[Journal](https://link.springer.com/article/10.1007/s11263-020-01335-w)] [[Pre-print](https://arxiv.org/abs/1906.04910)] ----- ![ ](fig/acd.png width="20%") [ECCV 2020] **Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions** _**Matheus Gadelha**`*`, Aruni RoyChowdhury`*`, Gopal Sharma, Evangelos Kalogerakis, Liangliang Cao, Erik Learned-Miller, Rui Wang, Subhransu Maji_ [[Paper](https://arxiv.org/pdf/2003.13834.pdf)] [[Project Page](selfsupacd/index.html)] ----- ![ ](fig/dmp_snapshot.png width="20%") **Deep Manifold Prior** _**Matheus Gadelha**, Rui Wang, Subhransu Maji_ **Best poster honorable mention at [NECV](http://visual.cs.brown.edu/workshops/necv2019/)**. [[Paper](https://arxiv.org/pdf/2004.04242.pdf)] ----- ![ ](shapehandles/fig/snapshot.png width="20%") [CVPR 2020] **Learning Generative Models of Shape Handles** _**Matheus Gadelha**, Giorgio Gori, Duygu Ceylan, Radomir Mech, Nathan Carr, Tamy Boubekeur, Rui Wang, Subhransu Maji_ [[Project Page](shapehandles/index.html)] ----- ![ ](shaperec/fig/abstract.png width="20%") [ICCV 2019] **Shape Reconstruction with Differentiable Projections and Deep Priors ** _**Matheus Gadelha**, Rui Wang, Subhransu Maji_ [[Paper](shaperec/dsp_paper.pdf)] [[Project Page](shaperec/index.html)] ----- ![ ](fig/bayesdip.png width="20%") [CVPR 2019] **A Bayesian Perspective on the Deep Image Prior ** _Zezhou Cheng, **Matheus Gadelha**, Subhransu Maji, Daniel Sheldon_ [[Paper](https://arxiv.org/abs/1904.07457)] [[Project Page](https://people.cs.umass.edu/~zezhoucheng/gp-dip/)] ----- ![ ](https://people.cs.umass.edu/~jcsu/papers/shape_recog/advers_examples.png width="20%") [ECCV 2018 - 3DRMS Workshop] **A Deeper Look at 3D Shape Classifiers ** _Jong-Chyi Su, **Matheus Gadelha**, Rui Wang, Subhransu Maji_ [[Paper](https://arxiv.org/abs/1809.02560)] [[Project Page](https://people.cs.umass.edu/~jcsu/papers/shape_recog/)]
----- ![ ](mrt/fig/smallabs.png width="20%") [ECCV 2018] **Multiresolution Tree Networks for Point Cloud Processing ** _**Matheus Gadelha**, Rui Wang, Subhransu Maji_ [[Paper](https://arxiv.org/abs/1807.03520)] [[Project Page](mrt/index.html)]
----- ![ ](prgan/fig/overview.png width="20%") [3DV 2017] **Unsupervised 3D Shape Induction from 2D Views of Multiple Objects ** _**Matheus Gadelha**, Subhransu Maji, Rui Wang_ [[Paper](https://arxiv.org/pdf/1612.05872.pdf)] [[Project Page](prgan/index.html)]
----- ![ ](fig/sketch.png width="20%") [3DV 2017] **3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks ** _Zhaoliang Lun, **Matheus Gadelha**, Evangelos Kalogerakis, Subhransu Maji, Rui Wang_ [[ArXiv](https://arxiv.org/abs/1707.06375)] [[Project Page](https://people.cs.umass.edu/~zlun/papers/SketchModeling/)] ----- ![ ](sppc/fig/airplanes_sorting_new2.png width="20%") [BMVC 2017] **Shape Generation using Spatially Partitioned Point Clouds ** _**Matheus Gadelha**, Subhransu Maji, Rui Wang_ [[ArXiv](https://arxiv.org/abs/1707.06267)] [[Project Page](sppc/index.html)] (#) Reviewing I worked/am working as a reviewer for the following venues: * SIGGRAPH 2023 * CVPR 2018-2023 (**2021 outstanding reviewer**) * ICCV 2019-2023 * ECCV 2018-2023 * ICLR 2021 * TPAMI (2018, 2021, 2023) * Computer and Graphics 2018 * SIGGRAPH Asia 2018 * Pacific Graphics 2019 I worked/am working as AC for the following venues: * WACV 2023 (#) Open Source (##) Interactive Mesh Deformation w/ ARAP Surface Modeling ![As Rigid as Possible Interactive Demo](https://www.youtube.com/watch?v=QUtpoybhYA8) Implementation of the ARAP Surface Modeling paper. It includes a software to deform any mesh, applying the computed transformation in real time. Made using C++ with Eigen and OpenGL. [[code](https://github.com/matheusgadelha/Pintar)] (##) Rigid Body Simulation Rigid body simulator coded in C++ with Eigen library and OpenGL. The code includes a demo where you can load any model and interactively draw forces. [[code](https://github.com/matheusgadelha/Pintar)] (##) Subdivision Surface ![Smoothing bunnies w/ subdivision surfaces.](fig/bunny_gets_better.png width="25%") Code in C++ to perform subdivision of a closed triangular mesh. Made from scratch, so no libraries are required. [[code](https://github.com/matheusgadelha/SubdivisionSurfaces)] (##) Generic A* implementation and CSP solver Template-based implementation for the A* algorithm and CSP solver written in C++. It is a generic solver, where you can simply define the successor and heuristic function for each problem. Includes examples on solving knight shortest path problem and the classic TSP (w/ Minimum Spanning Tree heuristic). CSP solver includes an efficient sudoku solver example. [[A* code](https://github.com/matheusgadelha/AStar)] [[CSP code](https://github.com/matheusgadelha/CSPSolver)]