ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation | Paper Citation Record

Observation f4bc9b23-a3d1-4741-9724-b54097bb2d32 · outbound

This paper cites End-to- end object detection with transformers.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation End-to- end object detection with transformers

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:09.496673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 243725e2-116e-49cf-b6c0-07b571f0c54f · outbound

This paper cites Efficient geometry-aware 3d generative adversarial networks.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Efficient geometry-aware 3d generative adversarial networks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:09.569394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e69625b-52cd-4155-9944-77ad387e8e63 · outbound

This paper cites Dora: Sampling and benchmarking for 3d shape varia- tional auto-encoders.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Dora: Sampling and benchmarking for 3d shape varia- tional auto-encoders

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:09.640689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8128c4d5-e360-4576-80fd-4e875df22c51 · outbound

This paper cites Pra-net: Point relation-aware network for 3d point cloud analysis.IEEE Transactions on Image Processing, 30:4436– 4448, 2021.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Pra-net: Point relation-aware network for 3d point cloud analysis.IEEE Transactions on Image Processing, 30:4436– 4448, 2021

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:09.692172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad43af98-8d42-4927-9a55-ec4a27ff9fb0 · outbound

This paper cites Objaverse: A universe of annotated 3d objects.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Objaverse: A universe of annotated 3d objects

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:09.775279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0071e4ef-9880-44cd-ad14-fe57931e7b51 · outbound

This paper cites Scaling recti- fied flow transformers for high-resolution image synthesis.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Scaling recti- fied flow transformers for high-resolution image synthesis

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:09.819860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96258909-e627-4d0a-9471-42a7857268a3 · outbound

This paper cites Tango3D: Towards Alignment for Global and Local 2D-3D Correspondence.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Tango3D: Towards Alignment for Global and Local 2D-3D Correspondence

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:09.938371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16370aa7-d37c-479f-9e06-ad9cbe18fa88 · outbound

This paper cites Efficientdreamer: High-fidelity and robust 3d cre- ation via orthogonal-view diffusion priors.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Efficientdreamer: High-fidelity and robust 3d cre- ation via orthogonal-view diffusion priors

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:09.985976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 627ff360-66d8-44bc-9be3-4a943731b383 · outbound

This paper cites Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:10.094394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d13b94b-4b53-41d5-a6b6-a62a14fbe975 · outbound

This paper cites No other representation component is needed: Diffusion transformers can provide representation guidance by themselves.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation No other representation component is needed: Diffusion transformers can provide representation guidance by themselves

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:10.203843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7207993f-8f93-4e29-9535-a216baecb52d · outbound

This paper cites Shap-E: Generating Conditional 3D Implicit Functions.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Shap-E: Generating Conditional 3D Implicit Functions

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:10.264312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f625a36-b9ba-42fe-92c3-ad0e8a228171 · outbound

This paper cites Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:10.360297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2af96906-3d2d-4cb2-9ae2-7829f81f5421 · outbound

This paper cites Repa-e: Unlocking vae for end-to-end tuning with latent diffusion transformers.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Repa-e: Unlocking vae for end-to-end tuning with latent diffusion transformers

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:10.466591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a12de9e-e74a-4d09-99f4-860fb765ba06 · outbound

This paper cites Craftsman3d: High-fidelity mesh generation with 3d native diffusion and interactive geometry refiner.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Craftsman3d: High-fidelity mesh generation with 3d native diffusion and interactive geometry refiner

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:10.634132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe53b9c9-4389-4494-8738-7c9b8998fa8f · outbound

This paper cites Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:10.752901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f168545a-5a59-4139-a046-85fdd4167e13 · outbound

This paper cites Hsgan: Hierarchical graph learning for point cloud generation.IEEE Transactions on Image Processing, 30:4540–4554, 2021.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Hsgan: Hierarchical graph learning for point cloud generation.IEEE Transactions on Image Processing, 30:4540–4554, 2021

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:10.920820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 181185c2-88f6-424c-979b-560712e76f34 · outbound

This paper cites Triposg: High-fidelity 3d shape synthesis using large-scale rectified flow models.IEEE Transactions on Pattern Analysis and Machine Intelligence,.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Triposg: High-fidelity 3d shape synthesis using large-scale rectified flow models.IEEE Transactions on Pattern Analysis and Machine Intelligence,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.049386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f747e29-1fae-422c-a4e1-1056fdadac01 · outbound

This paper cites Pointmamba: A simple state space model for point cloud analysis.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Pointmamba: A simple state space model for point cloud analysis

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.120404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 511ee524-da60-482e-8af6-e405cbe14476 · outbound

This paper cites Parameter-efficient fine-tuning in spectral domain for point cloud learning.IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 2025.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Parameter-efficient fine-tuning in spectral domain for point cloud learning.IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 2025

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.198360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f11127c-6530-47df-b803-d21687abf392 · outbound

This paper cites Meta architecture for point cloud analysis.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Meta architecture for point cloud analysis

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.242675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47883420-d420-4a8d-a26a-fd2a7d1d44e8 · outbound

This paper cites Pufa-gan: A frequency-aware generative adversarial network for 3d point cloud upsampling.IEEE Transactions on Image Processing, 31:7389–7402, 2022.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Pufa-gan: A frequency-aware generative adversarial network for 3d point cloud upsampling.IEEE Transactions on Image Processing, 31:7389–7402, 2022

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.337895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdad3f96-082c-40e3-b21b-dd99bae7a427 · outbound

This paper cites Openshape: Scaling up 3d shape representation towards open-world understanding.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Openshape: Scaling up 3d shape representation towards open-world understanding

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.374934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 939404b7-bf0a-458f-8345-ec7c3493bded · outbound

This paper cites Point-E: A System for Generating 3D Point Clouds from Complex Prompts.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Point-E: A System for Generating 3D Point Clouds from Complex Prompts

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.430164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cad2e6e-55de-4a2e-88e9-bee72d872c50 · outbound

This paper cites Dinov2: Learning robust visual features without supervision.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Dinov2: Learning robust visual features without supervision

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.502436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90f7e4b2-77ee-47fb-b419-9d25d52661e8 · outbound

This paper cites Masked autoencoders for point cloud self-supervised learning.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Masked autoencoders for point cloud self-supervised learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.589862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1988f5ea-e35c-48e5-adf7-81aa2566cfa9 · outbound

This paper cites Dreamfusion: Text-to-3d using 2d diffusion.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Dreamfusion: Text-to-3d using 2d diffusion

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.667893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8ff291c-6026-4f7a-bf49-f3086413e9eb · outbound

This paper cites Pointnet: Deep learning on point sets for 3d classification and segmentation.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Pointnet: Deep learning on point sets for 3d classification and segmentation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.762583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d42e7a2e-98db-4fc4-a160-4f782caf15ce · outbound

This paper cites Contrast with reconstruct: Contrastive 3d representation learning guided by generative pretraining.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Contrast with reconstruct: Contrastive 3d representation learning guided by generative pretraining

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.871860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f712fd36-152d-4d4b-b94a-365a96a9c271 · outbound

This paper cites Shapellm: Universal 3d object understanding for embodied interaction.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Shapellm: Universal 3d object understanding for embodied interaction

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:11.977569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4df6eee-85cb-444c-803a-03c52ff76657 · outbound

This paper cites Pointnext: Revisiting pointnet++ with improved training and scaling strategies.Proc.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Pointnext: Revisiting pointnet++ with improved training and scaling strategies.Proc

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:12.054362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06f5d716-1b5d-4e72-ae55-d71b34162ce0 · outbound

This paper cites Global-local bidi- rectional reasoning for unsupervised representation learning of 3d point clouds.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Global-local bidi- rectional reasoning for unsupervised representation learning of 3d point clouds

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:12.120752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e7d193f-c0c8-43b8-b59d-7ab5cb53041c · outbound

This paper cites Mvdream: Multi-view diffusion for 3d gen- eration.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Mvdream: Multi-view diffusion for 3d gen- eration

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:12.176834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e74d7d7-06f4-44e2-b718-b6726cef67c8 · outbound

This paper cites 3d neural field generation using triplane diffusion.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation 3d neural field generation using triplane diffusion

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:12.256248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bb6c6c6-a536-47fd-8b4e-d4794d6a94ad · outbound

This paper cites Meshgpt: Generating triangle meshes with decoder-only transformers.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Meshgpt: Generating triangle meshes with decoder-only transformers

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:12.396335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd312a6e-3988-4222-ac5b-a58b46c325b5 · outbound

This paper cites What mat- ters for representation alignment: Global information or spa- tial structure? InProc.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation What mat- ters for representation alignment: Global information or spa- tial structure? InProc

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:12.503265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cc6ecea-2e5e-4da1-92fa-08053ca4897f · outbound

This paper cites X-3d: Explicit 3d structure modeling for point cloud recog- nition.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation X-3d: Explicit 3d structure modeling for point cloud recog- nition

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:12.607231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 315099a9-3283-4acc-926e-def3c04d2652 · outbound

This paper cites U-repa: Aligning diffu- sion u-nets to vits.arXiv preprint arXiv:2503.18414, 2025.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation U-repa: Aligning diffu- sion u-nets to vits.arXiv preprint arXiv:2503.18414, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:12.726289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b816a8cd-4aac-4527-afe9-f24affda0c74 · outbound

This paper cites TripoSR: Fast 3D Object Reconstruction from a Single Image.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation TripoSR: Fast 3D Object Reconstruction from a Single Image

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:12.859071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e730d741-5d7e-4832-8b63-f6537df78446 · outbound

This paper cites Lion: Latent point dif- fusion models for 3d shape generation.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Lion: Latent point dif- fusion models for 3d shape generation

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:12.979821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bafded51-9938-4c4a-b24c-d89f313e4105 · outbound

This paper cites Cad: Photorealistic 3d generation via adversarial distillation.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Cad: Photorealistic 3d generation via adversarial distillation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:13.126607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 093789e1-b45f-481f-9f2f-b4ccb26f7820 · outbound

This paper cites Gpsformer: A global perception and local struc- ture fitting-based transformer for point cloud understanding.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Gpsformer: A global perception and local struc- ture fitting-based transformer for point cloud understanding

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:13.235088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87f14773-2805-43b9-bc2a-fa97746ad643 · outbound

This paper cites Rethinking masked representation learning for 3d point cloud understanding.IEEE Transactions on Im- age Processing, 34:247–262, 2024.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Rethinking masked representation learning for 3d point cloud understanding.IEEE Transactions on Im- age Processing, 34:247–262, 2024

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:13.310343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1db4c2a1-0dd7-4b07-82b9-bb457d464977 · outbound

This paper cites Score jacobian chaining: Lifting pretrained 2d diffusion models for 3d generation.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Score jacobian chaining: Lifting pretrained 2d diffusion models for 3d generation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:13.395646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32c96b76-45fe-4de7-bda9-489447d08c1a · outbound

This paper cites Vggt: Vi- sual geometry grounded transformer.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Vggt: Vi- sual geometry grounded transformer

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:13.531033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80973a0a-ccea-4655-a1cd-01b96b570ebf · outbound

This paper cites Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distilla- tion.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distilla- tion

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:13.727567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 328d9fec-2dae-4597-82b5-f8b0e11743f2 · outbound

This paper cites Representation entanglement for genera- tion: Training diffusion transformers is much easier than you think.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Representation entanglement for genera- tion: Training diffusion transformers is much easier than you think

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:13.861753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed2801e8-eb09-4515-baf2-64145eecb051 · outbound

This paper cites Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:14.056390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7bca9cb-3d34-4174-a2fc-8f4029c89555 · outbound

This paper cites Direct3d-s2: Gigascale 3d generation made easy with spatial sparse attention.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Direct3d-s2: Gigascale 3d generation made easy with spatial sparse attention

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:14.235914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93534359-e24c-48ea-a993-7a6563414e93 · outbound

This paper cites Point transformer v2: Grouped vector at- tention and partition-based pooling.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Point transformer v2: Grouped vector at- tention and partition-based pooling

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:14.394398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f753728f-1ac7-4ad6-88da-07ec3f7246b3 · outbound

This paper cites Point transformer v3: Simpler faster stronger.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Point transformer v3: Simpler faster stronger

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:14.541979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71d980f9-8da7-4f50-89fb-89f87e4d2fda · outbound

This paper cites Structured 3d latents for scalable and versatile 3d gen- eration.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Structured 3d latents for scalable and versatile 3d gen- eration

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:14.604312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2cc0a3f-2612-4c94-97aa-66769cace9a6 · outbound

This paper cites Ulip: Learning a unified representation of language, images, and point clouds for 3d understanding.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Ulip: Learning a unified representation of language, images, and point clouds for 3d understanding

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:14.763745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cf565f3-90ce-459f-beb3-1e1ff2d9f8c9 · outbound

This paper cites Ulip-2: Towards scal- able multimodal pre-training for 3d understanding.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Ulip-2: Towards scal- able multimodal pre-training for 3d understanding

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:14.866551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba4611a3-26f5-45b2-8dca-98c7d96bb8b1 · outbound

This paper cites Single- view 3d mesh reconstruction for seen and unseen categories.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Single- view 3d mesh reconstruction for seen and unseen categories

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:14.971134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b22399ca-d5db-48e4-85ad-a85c387bc07c · outbound

This paper cites Hi3dgen: High-fidelity 3d geometry generation from images via normal bridging.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Hi3dgen: High-fidelity 3d geometry generation from images via normal bridging

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:15.038820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86226d67-db45-4576-89e7-577d40bf87c2 · outbound

This paper cites Homugan: A 3d-aware gan with the method of cylindrical spatial-constrained sampling.IEEE Transactions on Image Processing, 34:320–334, 2024.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Homugan: A 3d-aware gan with the method of cylindrical spatial-constrained sampling.IEEE Transactions on Image Processing, 34:320–334, 2024

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:15.092179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4d9c050-0a0d-4156-b4d5-c8d829c83bb1 · outbound

This paper cites Representation alignment for generation: Training diffusion transformers is easier than you think.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Representation alignment for generation: Training diffusion transformers is easier than you think

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:15.190903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b8f2c95-62c8-4b66-abc5-575342e455c5 · outbound

This paper cites Pointclip: Point cloud understanding by clip.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Pointclip: Point cloud understanding by clip

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:15.328354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cebf950-79f6-450a-9e67-f5bceb1ee296 · outbound

This paper cites Hypergraph spectral analysis and processing in 3d point cloud.IEEE Transactions on Image Processing, 30:1193–1206, 2020.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Hypergraph spectral analysis and processing in 3d point cloud.IEEE Transactions on Image Processing, 30:1193–1206, 2020

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:15.395982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df4f8b77-4834-4f0b-bf41-66a20757a833 · outbound

This paper cites Vide- orepa: Learning physics for video generation through rela- tional alignment with foundation models.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Vide- orepa: Learning physics for video generation through rela- tional alignment with foundation models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:15.549114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1629ba9-9c2a-433f-aa12-524b181ff116 · outbound

This paper cites Point transformer.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Point transformer

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:15.635219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74a889fe-a8cf-4783-a5ee-6931c4696ba6 · outbound

This paper cites Uni3d: Exploring unified 3d representation at scale.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Uni3d: Exploring unified 3d representation at scale

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:15.680284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3147d8b-a000-4bf3-bb46-f6bbc1a425a4 · outbound

This paper cites Recur- rent diffusion for 3d point cloud generation from a single image.IEEE Transactions on Image Processing, 2025.

ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation Recur- rent diffusion for 3d point cloud generation from a single image.IEEE Transactions on Image Processing, 2025

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:15.767649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers