Difan Liu

Difan Liu

Auto-generated profile, based on publicly available information

Difan Liu

Adobe Research

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 November 2020
Verified
Book Chapter
Closed access
PDF file
GSGopal Sharma
Gopal Sharma
DLDifan Liu
Difan Liu
SMSubhransu Maji
Subhransu Maji
EKEvangelos Kalogerakis
Evangelos Kalogerakis
SCSiddhartha Chaudhuri
Siddhartha Chaudhuri
RMRadomír Měch
Radomír Měch

24 November 2024
Verified
Book Chapter
Closed access
PDF file
YRYixuan Ren
Yixuan Ren
YZYang Zhou
Yang Zhou
JYJimei Yang
Jimei Yang
JSJing Shi
Jing Shi
DLDifan Liu
Difan Liu
ASAbhinav Shrivastava
Abhinav Shrivastava

14 December 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
GSGopal Sharma
Gopal Sharma
RGRishabh Goyal
Rishabh Goyal
DLDifan Liu
Difan Liu
EKEvangelos Kalogerakis
Evangelos Kalogerakis
SMSubhransu Maji
Subhransu Maji
Constructive Solid Geometry (CSG) is a geometric modeling technique that defines complex shapes by recursively applying boolean operations on primitives such as spheres and cylinders. We present CSGNET, a deep network architecture that takes as input a 2D or 3D shape and outputs a CSG program that models it. Parsing shapes into CSG programs is desirable as it yields a compact and interpretable generative model. However, the task is challenging since the space of primitives and their combinations can be prohibitively large. CSGNET uses a convolutional encoder and recurrent decoder based on deep networks to map shapes to modeling instructions in a feed-forward manner and is significantly faster than bottom-up approaches. We investigate two architectures for this task --- a vanilla encoder (CNN) - decoder (RNN) and another architecture that augments the encoder with an explicit memory module based on the program execution stack. The stack augmentation improves the reconstruction quality of the generated shape and learning efficiency. Our approach is also more effective as a shape primitive detector compared to a state-of-the-art object detector. Finally, we demonstrate CSGNET can be trained on novel datasets without program annotations through policy gradient techniques.

22 July 2022 in ACM Transactions on Graphics
Verified
Journal Article
Open access
DLDifan Liu
Difan Liu
SSSandesh Shetty
Sandesh Shetty
THTobias Hinz
Tobias Hinz
MFMatthew Fisher
Matthew Fisher
RZRichard Zhang
Richard Zhang
EKEvangelos Kalogerakis
Evangelos Kalogerakis
We present ASSET, a neural architecture for automatically modifying an input high-resolution image according to a user's edits on its semantic segmentation map. Our architecture is based on a transformer with a novel attention mechanism. Our key idea is to sparsify the transformer's attention matrix at high resolutions, guided by dense attention extracted at lower image resolutions. While previous attention mechanisms are computationally too expensive for handling high-resolution images or are overly constrained within specific image regions hampering long-range interactions, our novel attention mechanism is both computationally efficient and effective. Our sparsified attention mechanism is able to capture long-range interactions and context, leading to synthesizing interesting phenomena in scenes, such as reflections of landscapes onto water or fora consistent with the rest of the landscape, that were not possible to generate reliably with previous convnets and transformer approaches. We present qualitative and quantitative results, along with user studies, demonstrating the effectiveness of our method. Our code and dataset are available at our project page: https://github.com/DifanLiu/ASSET

22 September 2020 in arXiv
Verified
Preprint
Open access
PDF file
GSGopal Sharma
Gopal Sharma
DLDifan Liu
Difan Liu
SMSubhransu Maji
Subhransu Maji
EKEvangelos Kalogerakis
Evangelos Kalogerakis
SCSiddhartha Chaudhuri
Siddhartha Chaudhuri
RMRadomír Měch
Radomír Měch
We propose a novel, end-to-end trainable, deep network called ParSeNet that decomposes a 3D point cloud into parametric surface patches, including B-spline patches as well as basic geometric primitives. ParSeNet is trained on a large-scale dataset of man-made 3D shapes and captures high-level semantic priors for shape decomposition. It handles a much richer class of primitives than prior work, and allows us to represent surfaces with higher fidelity. It also produces repeatable and robust parametrizations of a surface compared to purely geometric approaches. We present extensive experiments to validate our approach against analytical and learning-based alternatives. Our source code is publicly available at: https://hippogriff.github.io/parsenet.

31 March 2018 in arXiv
Verified
Preprint
Open access
PDF file
GSGopal Sharma
Gopal Sharma
RGRishabh Goyal
Rishabh Goyal
DLDifan Liu
Difan Liu
EKEvangelos Kalogerakis
Evangelos Kalogerakis
SMSubhransu Maji
Subhransu Maji
We present a neural architecture that takes as input a 2D or 3D shape and outputs a program that generates the shape. The instructions in our program are based on constructive solid geometry principles, i.e., a set of boolean operations on shape primitives defined recursively. Bottom-up techniques for this shape parsing task rely on primitive detection and are inherently slow since the search space over possible primitive combinations is large. In contrast, our model uses a recurrent neural network that parses the input shape in a top-down manner, which is significantly faster and yields a compact and easy-to-interpret sequence of modeling instructions. Our model is also more effective as a shape detector compared to existing state-of-the-art detection techniques. We finally demonstrate that our network can be trained on novel datasets without ground-truth program annotations through policy gradient techniques.