Search Results for author:
Found 9 papers, 6 papers with code
Learning and Simulation in Generative Structured World Models
The G-SWM not only unifies the key properties of previous models in a principled framework but also achieves two crucial new abilities, multi-modal uncertainty and situated behavior.
Improving Tuning-Free Real Image Editing with Proximal Guidance
Null-text inversion (NTI) optimizes null embeddings to align the reconstruction and inversion trajectories with larger CFG scales, enabling real image editing with cross-attention control.
Object-Centric Slot Diffusion
The recent success of transformer-based image generative models in object-centric learning highlights the importance of powerful image generators for handling complex scenes.
Generative Neurosymbolic Machines
In this paper, we propose Generative Neurosymbolic Machines, a generative model that combines the benefits of distributed and symbolic representations to support both structured representations of symbolic components and density-based generation.
Improving Generative Imagination in Object-Centric World Models
Third, a few key abilities for more faithful temporal imagination such as multimodal uncertainty and situation-awareness are missing.
SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability which is a main obstacle towards modeling real-world scenes.
SCALOR: Generative World Models with Scalable Object Representations
Scalability in terms of object density in a scene is a primary challenge in unsupervised sequential object-oriented representation learning.
RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation
Indoor semantic segmentation has always been a difficult task in computer vision.
Ranked #26 on
Semantic Segmentation
on SUN-RGBD
(using extra training data)
Incorporating Depth into both CNN and CRF for Indoor Semantic Segmentation
To improve segmentation performance, a novel neural network architecture (termed DFCN-DCRF) is proposed, which combines an RGB-D fully convolutional neural network (DFCN) with a depth-sensitive fully-connected conditional random field (DCRF).
