Search

Multi-view diffusion models, obtained by applying Supervised Finetuning (SFT) to text-to-image diffusion models, have driven recent breakthroughs in text-to-3D research. However, due to the limited size and quality of existing 3D datasets, they still suffer from multi-view inconsistencies and Neural Radiance Field (NeRF) reconstruction artifacts. We argue that multi-view diffusion models can benefit from further Reinforcement Learning Finetuning (RLFT), which allows models to learn from the data generated by themselves and improve beyond their dataset limitations during SFT. To this end, we introduce Carve3D, an improved RLFT algorithm coupled with a novel Multi-view Reconstruction Consistency (MRC) metric, to enhance the consistency of multi-view diffusion models. To measure the MRC metric on a set of multi-view images, we compare them with their corresponding NeRF renderings at the same camera viewpoints. The resulting model, which we denote as Carve3DM, demonstrates superior multi-view consistency and NeRF reconstruction quality than existing models. Our results suggest that pairing SFT with Carve3D's RLFT is essential for developing multi-view-consistent diffusion models, mirroring the standard Large Language Model (LLM) alignment pipeline. Our code, training and testing data, and video results are available at: https://desaixie.github.io/carve-3d., Comment: 22 pages, 16 figures. Our code, training and testing data, and video results are available at: https://desaixie.github.io/carve-3d. This paper has been accepted to CVPR 2024. v2: incorporated changes from the CVPR 2024 camera-ready version

We present Submerse, an end-to-end framework for visualizing flooding scenarios on large and immersive display ecologies. Specifically, we reconstruct a surface mesh from input flood simulation data and generate a to-scale 3D virtual scene by incorporating geographical data such as terrain, textures, buildings, and additional scene objects. To optimize computation and memory performance for large simulation datasets, we discretize the data on an adaptive grid using dynamic quadtrees and support level-of-detail based rendering. Moreover, to provide a perception of flooding direction for a time instance, we animate the surface mesh by synthesizing water waves. As interaction is key for effective decision-making and analysis, we introduce two novel techniques for flood visualization in immersive systems: (1) an automatic scene-navigation method using optimal camera viewpoints generated for marked points-of-interest based on the display layout, and (2) an AR-based focus+context technique using an auxiliary display system. Submerse is developed in collaboration between computer scientists and atmospheric scientists. We evaluate the effectiveness of our system and application by conducting workshops with emergency managers, domain experts, and concerned stakeholders in the Stony Brook Reality Deck, an immersive gigapixel facility, to visualize a superstorm flooding scenario in New York City.

The growing complexity of spatial and structural information in 3D data makes data inspection and visualization a challenging task. We describe a method to create a planar embedding of 3D treelike structures using their skeleton representations. Our method maintains the original geometry, without overlaps, to the best extent possible, allowing exploration of the topology within a single view. We present a novel camera view generation method which maximizes the visible geometric attributes (segment shape and relative placement between segments). Camera views are created for individual segments and are used to determine local bending angles at each node by projecting them to 2D. The final embedding is generated by minimizing an energy function (the weights of which are user adjustable) based on branch length and the 2D angles, while avoiding intersections. The user can also interactively modify segment placement within the 2D embedding, and the overall embedding will update accordingly. A global to local interactive exploration is provided using hierarchical camera views that are created for subtrees within the structure. We evaluate our method both qualitatively and quantitatively and demonstrate our results by constructing planar visualizations of line data (traced neurons) and volume data (CT vascular and bronchial data

Recent advances in high-resolution microscopy have allowed scientists to better understand the underlying brain connectivity. However, due to the limitation that biological specimens can only be imaged at a single timepoint, studying changes to neural projections is limited to general observations using population analysis. In this paper, we introduce NeuRegenerate, a novel end-to-end framework for the prediction and visualization of changes in neural fiber morphology within a subject, for specified age-timepoints.To predict projections, we present neuReGANerator, a deep-learning network based on cycle-consistent generative adversarial network (cycleGAN) that translates features of neuronal structures in a region, across age-timepoints, for large brain microscopy volumes. We improve the reconstruction quality of neuronal structures by implementing a density multiplier and a new loss function, called the hallucination loss.Moreover, to alleviate artifacts that occur due to tiling of large input volumes, we introduce a spatial-consistency module in the training pipeline of neuReGANerator. We show that neuReGANerator has a reconstruction accuracy of 94% in predicting neuronal structures. Finally, to visualize the predicted change in projections, NeuRegenerate offers two modes: (1) neuroCompare to simultaneously visualize the difference in the structures of the neuronal projections, across the age timepoints, and (2) neuroMorph, a vesselness-based morphing technique to interactively visualize the transformation of the structures from one age-timepoint to the other. Our framework is designed specifically for volumes acquired using wide-field microscopy. We demonstrate our framework by visualizing the structural changes in neuronal fibers within the cholinergic system of the mouse brain between a young and old specimen., Comment: Accepted for publication in IEEE Transactions on Visualization and Computer Graphics

Significant work has been done towards deep learning (DL) models for automatic lung and lesion segmentation and classification of COVID-19 on chest CT data. However, comprehensive visualization systems focused on supporting the dual visual+DL diagnosis of COVID-19 are non-existent. We present COVID-view, a visualization application specially tailored for radiologists to diagnose COVID-19 from chest CT data. The system incorporates a complete pipeline of automatic lungs segmentation, localization/ isolation of lung abnormalities, followed by visualization, visual and DL analysis, and measurement/quantification tools. Our system combines the traditional 2D workflow of radiologists with newer 2D and 3D visualization techniques with DL support for a more comprehensive diagnosis. COVID-view incorporates a novel DL model for classifying the patients into positive/negative COVID-19 cases, which acts as a reading aid for the radiologist using COVID-view and provides the attention heatmap as an explainable DL for the model output. We designed and evaluated COVID-view through suggestions, close feedback and conducting case studies of real-world patient data by expert radiologists who have substantial experience diagnosing chest CT scans for COVID-19, pulmonary embolism, and other forms of lung infections. We present requirements and task analysis for the diagnosis of COVID-19 that motivate our design choices and results in a practical system which is capable of handling real-world patient cases., Comment: 11 pages, 10 figures, accepted to IEEE VIS 2021 conference and IEEE Transactions on Visualization and Computer Graphics